Autonomic nervous system function evaluation system and autonomic nervous system function evaluation method

Abstract

This system enables autonomic nervous system function assessment while considering wearability, responsiveness, and reliability. [Solution] An autonomic nervous system function evaluation system comprising a processor and a memory device, wherein the memory device holds biological data measured over a predetermined period of time and autonomic nervous system function indices calculated based on biological data measured before a predetermined period of time, the processor determines the validity of the biological data measured over a predetermined period of time based on the biological data measured over a predetermined period of time and the autonomic nervous system function indices calculated based on biological data measured before a predetermined period of time, calculates autonomic nervous system function indices based on the data determined to be valid among the biological data measured over a predetermined period of time, and uses the autonomic nervous system function indices extracted based on specified extraction conditions to determine the validity of the biological data measured over a predetermined period of time, wherein the extraction conditions are conditions relating to the identification information, state, or attributes of a person.

Description

Technical Field

[0001] The present invention relates to an immediate (real-time) biological data evaluation technique used to improve the reliability of biological data measured in a short time when promoting the safe operation of transportation vehicles.

Background Art

[0002] In recent years, in order to prevent health-related accidents of drivers in the transportation industry, quantitative evaluation of the biological state has been carried out. Among the biological states, an evaluation of the autonomic nerve function based on the measurement of the beat-to-beat interval (BBI) data, which is the interval of heartbeats, by various types of heartbeat sensors that are easy to measure, has been implemented. In the evaluation of the autonomic nerve function during work, the immediacy of analysis and the reliability of data are important.

[0003] For example, in Japanese Unexamined Patent Application Publication No. 2020-130335 (Patent Document 1), focusing on the change tendency of biological signal with periodicity measured within an arbitrary time for the time-series data of a biological signal having periodicity with a missing section caused by measurement abnormality or the like, a time feature amount is accurately calculated. Specifically, an instantaneous heartbeat abnormal value is recognized from the measurement states of two adjacent R waves and excluded from the time-series data, and after performing interpolation using a linear function or the like that approximates the variation tendency of the interval (R-R Interval, RRI) of the R waves measured within a certain time, an activity index of the parasympathetic nerve obtained from the time feature amount (average heart rate, average RRI, length L of the long side and length T of the short side of the shape drawn by the Lorenz plot (LP) of adjacent RRIs, etc.) is calculated.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] It is crucial to be able to manage autonomic nervous system function assessments in real time during work, and a measurement and evaluation system is needed that comprehensively considers sensor wearability, responsiveness of analysis, and reliability of results.

[0006] During work involving driving, the person being evaluated (e.g., the driver) may not be in a resting state. Furthermore, when using wearable sensors designed for ease of wear to measure heart rate interval data, measurement errors are more likely to occur. The method described in Patent Document 1 may not adequately determine whether the heart rate interval is abnormal at the moment of measurement if the measurement time is short. Setting a longer measurement time reduces the responsiveness of the evaluation. Additionally, the wearable sensor may have memory capacity issues when trying to retain a large amount of heart rate interval data for extended periods. [Means for solving the problem]

[0007] To solve at least one of the above problems, the present invention provides an autonomic nervous system function evaluation system comprising a processor and a memory device, wherein the memory device holds biological data measured over a predetermined period of time and an autonomic nervous system function index calculated based on biological data measured before the predetermined period of time, and the processor determines the validity of the biological data measured over the predetermined period of time based on the biological data measured over the predetermined period of time and the autonomic nervous system function index calculated based on biological data measured before the predetermined period of time, and based on the data among the biological data measured over the predetermined period of time that is determined to be valid, the autonomic nervous system function evaluation system The system calculates autonomic function indices, stores the calculated autonomic function indices in the storage device as integrated autonomic function indice data, associating them with at least one of the following: identification information of the person whose biological data is being measured, the person's age, the person's gender, identification information of the vehicle the person is riding in, information indicating the person's work content, information regarding the sensor used to acquire the biological data, and the measurement time; and uses the autonomic function indices extracted from the integrated autonomic function indice data based on specified extraction conditions to determine the validity of the biological data measured over a predetermined period of time, wherein the extraction conditions are conditions relating to the person's identification information, state, or attributes. [Effects of the Invention]

[0008] Therefore, according to one aspect of the present invention, the validity of heart rate interval data acquired in a short time can be appropriately determined, and autonomic nervous system function evaluation that takes into account wearability, responsiveness, and reliability becomes possible.

[0009] Details of at least one embodiment of the subject matter disclosed herein are described in the accompanying drawings and the following description. Other features, aspects and effects of the subject matter disclosed are made apparent by the following disclosures, drawings and claims. [Brief explanation of the drawing]

[0010] [Figure 1]This is a block diagram showing an example of the main configuration of a biological data evaluation system according to an embodiment of the present invention. [Figure 2] This is a functional block diagram showing an example of the configuration of a rapid-response autonomic nervous system function evaluation system according to an embodiment of the present invention. [Figure 3] This flowchart shows an example of the processing performed by the correction processing unit according to an embodiment of the present invention. [Figure 4A] This is an explanatory diagram showing an example of the heart rate interval measured in an embodiment of the present invention and an autonomic nervous system function index based thereon. [Figure 4B] This is an explanatory diagram showing an example of the heart rate interval measured in an embodiment of the present invention and an autonomic nervous system function index based thereon. [Figure 4C] This is an explanatory diagram showing an example of the heart rate interval measured in an embodiment of the present invention and an autonomic nervous system function index based thereon. [Figure 4D] This is an explanatory diagram showing an example of the heart rate interval measured in an embodiment of the present invention and an autonomic nervous system function index based thereon. [Figure 5] This is an explanatory diagram showing an example of a list of multivariate autonomic nervous system function indicators measured in embodiments of the present invention. [Figure 6A] This is an explanatory diagram showing an example of heart rate interval data held by a rapid response autonomic nervous system function evaluation system according to an embodiment of the present invention. [Figure 6B] This is an explanatory diagram showing an example of autonomic nervous system function index data, including multivariate autonomic nervous system function, held by the rapid-response autonomic nervous system function evaluation system according to an embodiment of the present invention. [Figure 6C] This is an explanatory diagram showing an example of the internal structure of the ANF index integrated database held by the rapid-response autonomic nervous system function evaluation system according to an embodiment of the present invention. [Figure 7A] This is an explanatory diagram showing an example of validity determination based on LP within a predetermined analysis window in an embodiment of the present invention. [Figure 7B] This is an explanatory diagram showing an example of validity determination based on LP within a predetermined analysis window in an embodiment of the present invention. [Figure 7C] This is an explanatory diagram showing an example of validity determination based on LP within a predetermined analysis window in an embodiment of the present invention. [Figure 8A] It is an explanatory diagram showing an example of a method for calculating a valid region when a reference ANF index can be extracted from an ANF index integrated DB in an embodiment of the present invention. [Figure 8B] It is an explanatory diagram showing an example of a method for calculating a valid region when a reference ANF index can be extracted from an ANF index integrated DB in an embodiment of the present invention. [Figure 9] It is an explanatory diagram showing an example of a process in which a confidence interval extraction unit according to an embodiment of the present invention evaluates the reliability of analysis time data and extracts a confidence interval. [Figure 10] It is an explanatory diagram showing an example of display of an evaluation result at the current time by an immediate-response type autonomic nerve function evaluation system according to an embodiment of the present invention. [Figure 11] It is an explanatory diagram showing an example of display of evaluation results in a time series by an immediate-response type autonomic nerve function evaluation system according to an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0012] <System Configuration> FIG. 1 is a block diagram showing an example of the main configuration of a biological data evaluation system according to an embodiment of the present invention.

[0013] The biological data evaluation system of this embodiment includes an immediate-response type autonomic nerve function evaluation system 1 that processes biological data received from one or more vehicles 7 via a network.

[0014] Vehicle 7 includes a GNSS (Global Navigation Satellite System) 8A for measuring the position of vehicle 7, an inter-vehicle distance sensor 8B for measuring the distance between vehicle 7 and vehicles traveling in front of and behind it, a speedometer 8C for measuring the speed of vehicle 7, an acceleration sensor 8D for measuring the acceleration of vehicle 7, a camera 8E for taking pictures of the area around vehicle 7, and an on-board information collection device 10 that collects measurement data and image data from these and transmits them to the rapid response autonomic nervous system function evaluation system 1.

[0015] Furthermore, the vehicle 7 is equipped with a biosensor 11, a biometric data collection device 12, a sensor information input unit 13, a sensor information collection device 14, a user information setting unit 15, a user information collection device 16, a work content setting unit 17, and a work information collection device 18. These may be attached to the vehicle 7, or they may be carried by the user (for example, the driver of the vehicle 7) and brought into the vehicle 7 when driving it.

[0016] The biosensor 11 includes a sensor that detects heart rate (RRI or PPI) based on an electrocardiogram, pulse wave, or heart sounds.

[0017] In addition to a heart rate sensor, the biosensor 11 can employ sensors that detect sweating, body temperature, blinking, eye movements, electromyography, or electroencephalography. The biosensor 11 can be a wearable device that can be worn by the driver, a sensing device attached to any part of the vehicle 7 such as the steering wheel, seat, or seat belt, or an image recognition system that captures and analyzes the driver's facial expressions or behavior.

[0018] The biometric data collection device 12 collects the information measured by the biosensor 11 and transmits it to the rapid response autonomic nervous system function evaluation system 1.

[0019] The sensor information input unit 13 has the function of receiving input information about the biosensor 11. The information about the biosensor 11 may include, for example, information about the type, model, version, specifications, and settings of the biosensor 11. The sensor information collection device 14 collects the information input to the sensor information input unit 13 and transmits it to the rapid response autonomic nervous system function evaluation system 1.

[0020] The user information setting unit 15 has the function of receiving settings related to the user. User information may include, for example, the user's name, identification information, age, gender, affiliation, and job responsibilities. The user information collection device 16 collects the information set in the user information setting unit 15 and transmits it to the rapid response autonomic nervous system function evaluation system 1.

[0021] The work content setting unit 17 has a function to accept settings related to the user's work. This information may include, for example, the content of the work performed by the user (e.g., driving, loading, unloading, and taking breaks) and information such as the time period during which the work was performed. The work information collection device 18 collects the information set in the work content setting unit 17 and transmits it to the rapid response autonomic nervous system function evaluation system 1.

[0022] The biosensor 11, biometric data collection device 12, sensor information input unit 13, sensor information collection device 14, user information setting unit 15, user information collection device 16, work content setting unit 17, and work information collection device 18 may each be independent devices, but at least some of them may be implemented by a single device. For example, the biosensor 11 may be a sensor device worn by the user, and the biometric data collection device 12 may be a terminal device carried by the user (user terminal) or a terminal device attached to the vehicle 7 (in-vehicle terminal). In addition, the sensor information input unit 13, sensor information collection device 14, user information setting unit 15, user information collection device 16, work content setting unit 17, and work information collection device 18 may be implemented as applications for the user terminal or in-vehicle terminal.

[0023] Although Figure 1 shows only one vehicle 7 and one set of biosensors 11 to business information collection device 18, an actual biometric data evaluation system may include multiple vehicles 7 and multiple sets of biosensors 11 to business information collection devices 18 to accommodate multiple users. The type of biosensor 11 used may differ for each user, and even for the same user, the type of biosensor 11 may differ from day to day.

[0024] The rapid response autonomic nervous system function evaluation system 1 is a computer that includes a processor 2, a memory 3, a storage device 4, an input / output device 5, and a communication device 6. The memory 3 includes a heart rate interval acquisition unit 21 that acquires heart rate intervals within a unit time according to sensor information, a correction processing unit 22 that performs correction processing to improve the reliability of the heart rate interval data, an ANF index calculation unit 23 that calculates an autonomic nervous system function (ANF) index from the corrected heart rate interval data, and a data integration unit 24 that integrates ANF index data with user information and sensor information and business information. The integrated data is stored in the ANF index integration DB 48. The memory 3 further includes an evaluation result display unit 25 that comprehensively evaluates the integrated ANF index and displays the evaluation results. The memory 3 also further includes a setting unit 26 (see Figure 2) for setting the display items of the evaluation results.

[0025] The correction processing unit 22 includes a reference ANF index extraction unit 31 that extracts ANF indices to be referenced from the ANF index integrated DB 48, a validity determination unit 32 (see Figure 2, the same applies hereinafter) that determines the validity of heart rate interval data based on a Lorentz plot (LP), a noise reduction / interpolation processing unit 33 that performs noise reduction and interpolation of heart rate interval data based on the determination result, and a confidence interval extraction unit 34 that evaluates the reliability of data within a predetermined time period using the processed data and extracts a confidence interval.

[0026] In this embodiment, the functions of the heart rate interval acquisition unit 21, correction processing unit 22, ANF index calculation unit 23, data integration unit 24, evaluation result display unit 25, and setting unit 26 are actually realized by the processor 2 executing instructions written in a program stored in memory 3. In other words, the processing performed by each of the above units in the following description is actually performed by the processor 2.

[0027] The storage device 4 stores heart rate sensor measurement data 41, user information 42, sensor information 43, business information 44, in-vehicle information 45, short-time BBI data 46, ANF index data 47, and an ANF index integrated DB 48. The heart rate sensor measurement data 41 includes data measured by the biosensor 11 and transmitted by the biometric data acquisition device 12. The user information 42 includes data set by the user information setting unit 15 and transmitted by the user information acquisition device 16. The sensor information 43 includes data input to the sensor information input unit 13 and transmitted by the sensor information acquisition device 14. The business information 44 includes data set by the business content setting unit 17 and transmitted by the business information acquisition device 18. The in-vehicle information 45 includes information collected and transmitted by the in-vehicle information acquisition device 10. This information includes, for example, information acquired from GNSS 8A, inter-vehicle distance sensor 8B, speedometer 8C, acceleration sensor 8D, and camera 8E.

[0028] Short-time BBI data 46 includes short-time (e.g., 2 minutes) BBI data. This data includes, for example, heart rate interval (BBI) data every 2 minutes acquired by the heart rate interval acquisition unit 21 from data transmitted from the biometric data acquisition device 12. ANF index data 47 includes data resulting from correction processing by the correction processing unit 22 and calculation of the ANF index by the ANF index calculation unit 23, applied to the BBI data. ANF index integrated DB 48 includes data that integrates the ANF index with user information and business information, etc.

[0029] <Processing Details> Figure 2 is a functional block diagram showing an example of the configuration of the rapid-response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0030] Heart rate sensor measurement data, sensor information, user information, work information, and in-vehicle information acquired from the user terminal and vehicle 7 are transmitted to the rapid response autonomic nervous system function evaluation system 1 via the network 19. To enable rapid response and evaluate autonomic nervous system function in real time during work, the acquisition time for sensor measurement data is kept short. For example, every two minutes of sensor measurement data is acquired, it is transmitted from the biometric data acquisition device 12 to the rapid response autonomic nervous system function evaluation system 1 and stored in the storage device 4 as heart rate sensor measurement data 41. Similarly, data transmitted from the sensor information acquisition device 14, user information acquisition device 16, work information acquisition device 18, and in-vehicle information acquisition device 10 are stored in the storage device 4 as sensor information 43, user information 42, work information 44, and in-vehicle information 45, respectively.

[0031] The heart rate interval acquisition unit 21 identifies the type of heart rate sensor that measured the heart rate sensor data 41 by referring to the sensor information 43 corresponding to the data, performs formatting processing according to the identified type of heart rate sensor, and converts it into a common format for BBI data of unit analysis time. The correction processing unit 22 performs data validity determination, noise reduction and interpolation processing, and extraction of highly reliable intervals on the acquired heart rate interval data.

[0032] A key feature of this embodiment is that the correction processing unit 22 includes a reference ANF index extraction unit 31 that extracts a reference ANF index from the ANF index integrated DB 48 accumulated up to the time of analysis of newly acquired short-term heart rate sensor measurement data 41. By using the accumulated reference ANF index to determine the validity range of the measurement data (i.e., the range of data judged to be valid) for short-term heart rate interval data that is prone to noise, the reliability of short-term data is improved.

[0033] Specifically, the correction processing unit 22 includes a validity determination unit 32. The validity determination unit 32 performs a validity determination on the data area on the LP and determines the validity of each measured heart rate interval data by returning the data that has been determined to be valid to the time series.

[0034] The noise reduction and interpolation processing unit 33 of the correction processing unit 22 performs interpolation on data that can be interpolated based on the trend of the acquired data, and removes data that cannot be interpolated as noise, for data that has been determined to be valid. Furthermore, the correction processing unit 22 has a confidence interval extraction unit 34. The confidence interval extraction unit 34 checks the location of time-series data loss for the data that has undergone noise reduction and interpolation processing, checks the continuity of good intervals with no (or few) losses, calculates a reliability score that takes into account the continuity and the time length of the usable data, and extracts confidence intervals suitable for calculating the ANF index.

[0035] Furthermore, the ANF index calculation unit 23 calculates the ANF index for the corresponding analysis time based on the corrected heart rate interval data. The data integration unit 24 integrates the ANF index, user information, business information, and in-vehicle information and stores them in the ANF index integration DB 48.

[0036] The user or administrator can comprehensively evaluate the analyzed ANF index data via the evaluation result display unit 25 and check the evaluation result for the current time or the trend of change over time. The evaluation result display unit 25 is also connected to the setting unit 26, and the display items, basic information, and analysis conditions may be changed by user input, etc.

[0037] Figure 3 is a flowchart showing an example of the processing performed by the correction processing unit 22 according to an embodiment of the present invention.

[0038] The heart rate interval acquisition unit 21 performs data formatting processing (step 303) according to the short-time BBI 301 acquired from the heart rate sensor measurement data 41 and the information 302 regarding the heart rate sensor that measured the data, acquired from the sensor information 43, to acquire standard-time heart rate interval data (BBI) for a predetermined short-time interval (e.g., 2 minutes). It is difficult to analyze heart rate variability with only one BBI (i.e., the interval between one beat and the next beat), and an analysis time window of a predetermined length is required. When responsiveness is important, it is preferable that the predetermined time be short, while when the reliability of the analysis is important, it is preferable that the predetermined time be longer than the time width required for heart rate variability analysis.

[0039] The validation determination unit 32 of the correction processing unit 22 determines whether advanced noise reduction is necessary based on the heart rate sensor information input for a predetermined short time and the quality of the acquired data (step 304). If it determines that advanced noise reduction is not necessary, it performs an outlier basic determination (step 305). On the other hand, if it determines that advanced noise reduction is necessary, the reference ANF index extraction unit 31 accesses the ANF index integrated DB 48 that has been stored up to the analysis time (step 306) and extracts reference ANF indices that satisfy certain extraction conditions. As an example of extraction conditions, data from the most recent predetermined time (e.g., 30 minutes) of the same user's work state as the current analysis time may be extracted as reference ANF indices. For example, if the predetermined short time is 2 minutes and the most recent predetermined time is 30 minutes, 15 sets of ANF indices will be extracted.

[0040] The above-mentioned "the most recent specified time in the same work state as the current analysis time of the same user" is just one example of an extraction condition, and other extraction conditions can be set. For example, data from users of a similar age to the user being analyzed, or data from users of the same gender, may be extracted. Alternatively, data from the same user in a resting state may be extracted, or data measured using a highly accurate biosensor 11 targeting the same user (or other users, or users with similar conditions such as age and gender) may be extracted.

[0041] Furthermore, examples of reference ANF indices include the mean RRI, the standard deviation SD1 in the Y=-X direction related to LP, and the standard deviation SD2 in the Y=X direction.

[0042] LP is a two-dimensional plot used for chaos analysis, in which the time series data T[t] at preceding time t (t=0, 1, 2, ...) is plotted on the x-axis, and the time series data T[t+dt] at time t+dt, which is obtained by a period dt (dt=1, 2, 3, ...) from time t, is plotted on the y-axis. In this example, an LP is shown where T[t] is plotted on the x-axis and T[t+dt] is plotted on the y-axis.

[0043] By analyzing the geometric figures drawn on the LP (Loop Pattern), the characteristics of the time series data T[t] can be analyzed. In particular, when an LP is drawn for RRI data over a continuous period, it is known that the geometric features of the LP allow for evaluation of measurement characteristics, such as the extent to which the data measured over a given period includes arrhythmias or measurement errors. In this embodiment, an example of the LP when dt=1 time point is shown. Furthermore, the case where the original series RRI[t] of the measured RRI data is used as the time series data is also shown.

[0044] If a reference ANF index can be extracted (Step 307: Yes), the validation unit 32 performs a validity check of the acquired BBI based on the reference index and the LP of the data to be analyzed (Step 308). The specific validity check will be explained later with reference to Figures 7A to 8B. On the other hand, an example of a case where a reference ANF index that satisfies the predetermined extraction conditions cannot be extracted is when the user's data cannot be extracted from the ANF index integration DB 48 during the initial sensor installation of the user. If a reference index cannot be extracted (Step 307: No), the validation unit 32 refers only to the BBI data of a predetermined analysis window, checks the geometric area on the LP, and performs a validity check of the data (Step 309). The specific calculation method will be explained later with reference to Figures 7A to 7C.

[0045] Next, the noise reduction and interpolation processing unit 33 performs interpolation on the data after validity has been determined, and removes any remaining abnormal data as noise (step 310). Specifically, the noise reduction and interpolation processing unit 33 converts the data whose validity has been determined on the LP back into time-series RRI data and checks the occurrence status and interval of abnormal data in the time series (i.e., data that was determined to be invalid on the LP). If the time interval of abnormal data occurrence is short and it is determined that interpolation is possible based on the change trend of the RRI data before and after within the analysis interval, using RRI data for several beats within the normal range, the noise reduction and interpolation processing unit 33 performs interpolation. After the interpolation processing, the noise reduction and interpolation processing unit 33 removes the data in the interval remaining as an abnormal value as noise, making it a missing interval in the time series.

[0046] Subsequently, the confidence interval extraction unit 34 extracts confidence intervals for calculating the ANF index according to the occurrence of missing intervals (step 311). An example of a specific method for calculating confidence intervals will be described later with reference to Figure 9.

[0047] Using BBI data that has undergone correction processing through a series of processes including reference ANF index extraction (step 306), validity determination by LP (step 308 or 309), noise reduction and interpolation processing (step 310), and confidence interval extraction (step 311), the ANF index calculation unit 23 calculates the ANF index for the corresponding analysis time and stores it as ANF index data 47 (step 312). The data integration unit 24 integrates the calculated ANF index with user information 42, sensor information 43, business information 44, and in-vehicle information 45, etc., and stores it in the ANF index integration DB 48 (step 313). The rapid-response autonomic nervous system function evaluation system 1 performs a comprehensive evaluation based on the integrated ANF index integration DB 48 and displays the evaluation result for the actual time of analysis, or the evaluation result over time, on the input / output device 5 via the evaluation result display unit 25.

[0048] Figures 4A to 4D are explanatory diagrams showing examples of heart rate intervals measured in embodiments of the present invention and autonomic nervous system function indices based thereon.

[0049] Figure 4A shows an example of RRI (RR Interval), which measures the interval between R waves in an electrocardiogram. Figure 4B shows an example of PPI (Peak-to-Peak Interval), which measures the interval between peaks in a pulse wave. In this embodiment, the heart rate interval BBI used to calculate the ANF index may be either RRI or PPI as described above. However, generally speaking, RRI is highly accurate because it measures the heart rate itself, but it places a heavy burden on the user, such as requiring the wearer to wear a belt or underwear with electrodes attached. In contrast, PPI can be measured using, for example, a wristwatch-type pulse sensor, and places less burden on the user, but it tends to have lower accuracy due to frequent measurement errors such as noise.

[0050] Figure 4C shows an example of the change in heart rate interval BBI (RRI or PPI) over time. Figure 4D shows the frequency analysis based on the BBI data for a predetermined analysis time window (e.g., 2 minutes) in Figure 4C, and displays the low-frequency component LF, high-frequency component HF, and total power TP, which are part of the ANF index. Here, LF is the power spectrum in a predetermined relatively low frequency band (e.g., 0.04 Hz to 0.15 Hz), HF is the power spectrum in a predetermined relatively high frequency band (e.g., 0.15 Hz to 0.4 Hz), and total power TP is the sum of LF and HF.

[0051] Figure 5 is an explanatory diagram showing an example of a list of multivariate autonomic nervous system function indices measured in embodiments of the present invention.

[0052] Based on BBI data within the analysis time window, numerous indices in the frequency domain, time domain, or nonlinear domain can be calculated to comprehensively evaluate autonomic nervous system function. Here, we will describe some representative indices.

[0053] Among the frequency domain indices, LF, HF, and TP are as explained with reference to Figure 4D, and LF / HF is the ratio of LF to HF. LF and HF are used as indices related to the sympathetic and parasympathetic nervous systems, respectively. Among the time domain indices, RRI is the interval of the R wave in the electrocardiogram, as explained earlier. Among the nonlinear domain indices, SD1 is the standard deviation of LP in the Y=-X direction, SD2 is the standard deviation of LP in the Y=X direction, and SD1 / SD2 is their ratio.

[0054] Figure 6A is an explanatory diagram showing an example of heart rate interval data held by the rapid response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0055] Specifically, the heart rate interval data shown in Figure 6A is an example of data included in the short-term BBI data 46. The RRI data measured at the time of measurement includes a list of combinations of user ID 601, vehicle ID 602, heart rate sensor 603, measurement time 604, and RRI 605. Here, an example is shown where the heart rate interval data includes RRI 605, but this is just one example of BBI data, and PPI may be stored instead of RRI.

[0056] User ID 601 and Vehicle ID 602 ​​are information that identifies the user being measured and the vehicle 7 that the user is riding in. Heart rate sensor 603 is information that identifies the heart rate sensor used for measurement (for example, information that identifies at least one of the type, model, or individual heart rate sensor). One line (one record) of heart rate interval data corresponds to one heartbeat, measurement time 604 is the time of appearance of each heartbeat (for example, the peak of the R wave or pulse wave, etc.), and RRI 605 indicates the time interval from the previous heartbeat to the current heartbeat. Here, RRI 605 is data on a scale of approximately several hundred milliseconds.

[0057] For example, the first row of Figure 6A shows that an R wave was measured at 10:00:00.000 on April 1, 2020, and the interval between that R wave and the previous R wave was 750 milliseconds. The second row shows that the R wave following the R wave in the first row was measured at 10:00:00.755 on April 1, 2020, and the interval between that R wave and the previous R wave (i.e., the R wave in the first row) was 755 milliseconds.

[0058] Figure 6B is an explanatory diagram showing an example of autonomic nervous system function index data, including multivariate autonomic nervous system function, held by the rapid response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0059] Specifically, the autonomic nervous system function (ANF) index data within a unit time shown in Figure 6B is an example of the data included in the ANF index data 47. Each row (1 record) of the ANF index data within a unit time shown in Figure 6B contains the ANF index calculated from BBI data over a predetermined short period (2 minutes in the example of Figure 6B). User ID 611, vehicle ID 612, and heart rate sensor 613 correspond to user ID 601, vehicle ID 602, and heart rate sensor 603 shown in Figure 6A, respectively. Date and time 614 indicates a time representative of each predetermined short period (for example, the start time).

[0060] The autonomic nervous system function index 615 is an ANF index calculated from BBI data for each predetermined short period, and may include, for example, at least one of the ANF indices shown in Figure 5. The reliability score 616 indicates the value of the reliability score, which is an index that evaluates the reliability of the ANF index calculated from BBI data for each predetermined short period. The method for calculating the reliability score will be described later with reference to Figure 9. The reference time 617 indicates the length of time of past ANF index data referenced for validating the BBI data. For example, if past ANF index data is not referenced, the value of reference time 617 will be 0. Also, if ANF index data from the past 30 minutes is referenced, the value of reference time 617 will be 30.

[0061] Noise reduction method 618 indicates the method used to validate the BBI data. For example, if validation is performed based on LP as described later, the value of noise reduction method 618 will be LP. Interpolation method 619 indicates the method (e.g., moving average) used to interpolate the BBI data that has been determined to be invalid (i.e., noisy) and removed.

[0062] Figure 6C is an explanatory diagram showing an example of the internal configuration of the ANF index integrated DB48 held by the rapid response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0063] The ANF index integrated DB48 shows a data structure that comprehensively lists user information 621, vehicle information 622, heart rate sensor information 623, time information 624, work information 625, autonomic nervous system function index 626, reliability score 627, and application method 628.

[0064] Here, user information 621, vehicle information 622, heart rate sensor information 623, and time information 624 correspond to user ID 611, vehicle ID 612, heart rate sensor 613, and date / time 614 shown in Figure 6B, respectively. Business information 625 is information about the business each user was performing at each time, extracted from business information 44. Autonomic nervous system function index 626 and reliability score 627 correspond to autonomic nervous system function index 615 and reliability score 616 shown in Figure 6B, respectively. Application method 628 corresponds to noise reduction method 618 and interpolation method 619 shown in Figure 6B.

[0065] Figures 7A to 7C are explanatory diagrams showing an example of validity determination based on LP within a predetermined analysis window in an embodiment of the present invention.

[0066] Specifically, Figures 7A to 7C illustrate the process performed in step 309 of Figure 3. In this case, the validation unit 32 generates LPs for BBI data within a predetermined time period, pairs preceding and succeeding BBI data, performs basic outlier removal, and confirms the data distribution within the initial normal range. As an example of the initial normal range, the median of the BBI data within the relevant time period may be calculated, and the range from median × 0.75 to median × 1.75 may be set as the initial normal range. In this case, BBI data outside the initial normal range is removed as outliers.

[0067] Furthermore, as an example of a data validity region on the LP, an elliptical shape may be virtually formed on the LP along the Y=X direction where the data is concentrated, and the internal region (elliptical region) may be set as the validity region. To determine the elliptical region based on the data concentration, the ellipse center, the vertical axis of the ellipse, and the horizontal axis of the ellipse are specified. Here, the axis in the y=-x direction of the ellipse is described as the vertical axis, and the axis in the y=x direction is described as the horizontal axis. All points within the initial normal range are projected onto the y=x axis and the y=-x axis. The average distance between the projection point on the y=x axis and the origin is m, and the position at a distance m from the origin on the y=x axis is set as the center position of the ellipse. The average of the BBI is

[0068]

number

[0069] If so, the center m in the y=x direction is

[0070]

number

[0071] It corresponds to this.

[0072] Furthermore, as an example of the horizontal axis (y=x direction) a of the ellipse, we use the value obtained by doubling the standard deviation in the y=x direction: std2. For data following a normal distribution, this corresponds to the range containing approximately 96% of the data. As an example of the vertical axis (y=-x direction) b of the ellipse, we use the value obtained by doubling the standard deviation in the y=-x direction: std1. The value of the horizontal axis (y=x direction) a is not necessarily greater than the value of the vertical axis (y=-x direction) b.

[0073] The standard deviation in the y=x direction refers to the standard deviation of the data when the target data set is projected onto the line y=x.

[0074] The standard deviation in the y=-x direction refers to the standard deviation of the data when the target data set is projected onto the line y=-x.

[0075] Figure 7B is an example of a LP (Low-Level) of BBI data, where each point on the plane in Figure 7B is a plot of BBI data. For example, if the heart rate interval data shown in Figure 6A is obtained, based on the data in the first and second rows, a point is plotted where the value of PPIt on the horizontal axis is 750 milliseconds and the value of PPIt+1 on the vertical axis is 755 milliseconds. Ellipse 701 has the center, horizontal axis length, and vertical axis length determined by the method described above. The area inside this ellipse 701 is the valid region. Figure 7C shows the state after removing the BBI data outside ellipse 701 as invalid.

[0076] Figures 8A and 8B are explanatory diagrams illustrating an example of a method for calculating the validity area in an embodiment of the present invention, where a reference ANF index can be extracted from the ANF index integration DB48.

[0077] Specifically, Figures 8A and 8B illustrate the process performed in step 308 of Figure 3. The ANF index is referenced for a unit of time for n points (e.g., n=15) of the same user under the same work conditions, going back in time. The shape of the validity region is an ellipse, similar to Figures 7A to 7C. As an example of referenced ANF indexes, MeanNN, Poincare SD1, and Poincare SD2, representing the average RRI in the ANF index list in Figure 5, are referenced.

[0078] The validity determination unit 32 fuses the distribution of BBI data on the LP within the analysis period with the extracted ANF index to determine a new validity region. As an example, the center of the ellipse is calculated as follows: the weighted average of the MeanNN of n points is calculated, multiplied by a coefficient to calculate the average with the average value of BBI within the analysis period (i.e., the above numerical value (1)), and the calculated average is multiplied by √2 to calculate the center position of y=x (formula (3)).

[0079]

number

[0080] For the horizontal axis of the ellipse (y=x direction), the weighted average of the standard deviation (SD2) of n points is calculated, and the average with the standard deviation (std2) over the analysis period is calculated by multiplying it by a coefficient (Equation (4)).

[0081]

number

[0082] For the vertical axis of the ellipse (y=-x direction), the weighted average of SD1 for n points is calculated, and the average with std1 over the analysis period is calculated by multiplying it by a coefficient (Equation (5)).

[0083]

number

[0084] The reference weight w can be the same for all n points, or points closer to the current time (in other words, newer measurement data) can be given a larger weight. The former corresponds to a moving average, and the latter corresponds to a weighted moving average. Furthermore, the weight α for the current time of analysis can be set to a value between 0.0 and 1.0, and the smaller this value, the more emphasis is placed on the trend of past reference ANF indicators.

[0085] You can assign the same set of weights to the center, horizontal axis, and vertical axis, or you can assign different sets of weights to each item.

[0086] The validity determination unit 32 determines the range of the validity area, then considers data within the area as good data and data outside the area as abnormal values.

[0087] Figure 8A shows an example of the results of determining validity using only BBI data within a predetermined short time period, without using a reference ANF index extracted from the ANF Index Integration DB48. In contrast, Figure 8B shows an example of the results of determining validity using the same BBI data within a predetermined short time period as in Figure 8A, in addition to a reference ANF index extracted from the ANF Index Integration DB48.

[0088] When using only BBI data from a predetermined short period, the small number of samples obtained can cause a significant bias in the overall distribution due to a small amount of noise, as shown by ellipse 801 in Figure 8A. As a result, BBI data that should be used to calculate the ANF index may be removed as outliers, or BBI data that should not be used to calculate the ANF index may be used as valid data. In contrast, when using a reference ANF index, the ANF index value is based on BBI data acquired over a certain period of time in the past. Therefore, as shown by ellipse 802, a valid region with less influence from a small amount of noise within a predetermined short period can be established. As a result, BBI data suitable for calculating the ANF index can be obtained.

[0089] In the example above, the center of the ellipse in the valid region is calculated based on the mean value of the BBI data, but the median can be used instead of the mean.

[0090] The noise reduction and interpolation processing unit 33 converts the good data whose validity has been determined on the LP back into time-series RRI data and checks the occurrence status and interval of abnormal data in the time series. If the time of the abnormal value occurrence interval is short and interpolation is possible using RRI data for several beats in the normal range based on the change trend of the RRI data before and after within the analysis interval, the noise reduction and interpolation processing unit 33 performs interpolation (step 310 in Figure 3). The noise reduction and interpolation processing unit 33 removes the data in the interval remaining as an abnormal value as noise and makes that interval a missing interval in the time series.

[0091] Figure 9 is an explanatory diagram showing an example of the process by which the confidence interval extraction unit 34 according to an embodiment of the present invention performs a reliability evaluation of the analysis time data and extracts a confidence interval.

[0092] Specifically, Figure 9 illustrates the process performed in step 311 of Figure 3. Validation and noise reduction / interpolation processing by LP clarifies the location of missing data within the analysis time. The confidence interval extraction unit 34 searches for continuous intervals of good data (i.e., data deemed valid by LP and data interpolated by the interpolation process) according to the missing data situation, and evaluates the reliability score to extract confidence interval data suitable for calculating the ANF index, thereby improving the reliability of the ANF index.

[0093] As a specific search method, we will explain an example where the analysis window width is 2 minutes. Ideally, all 2 minutes of BBI data should be acquired in good condition, but if outliers or missing values ​​are included, generally, if the continuous interval of good data is 60 seconds or longer, it will have a correlation of 80% or more when calculating the ANF index compared to the original good data. In this case, that is, when the 2 minutes of BBI data contains a continuous interval of good data of 60 seconds or longer, the method of extracting the data from that continuous interval as confidence interval data will be called shortening method 1.

[0094] Next, we experimentally confirmed that if a single long continuous interval cannot be extracted due to the location of missing data, an ANF index with accuracy close to that of shortening method 1 can be calculated by combining two or more short continuous intervals of 30 seconds or longer. In this case, that is, a method that extracts data from intervals formed by combining two or more continuous intervals of good data between 30 seconds and 60 seconds as confidence interval data will be called shortening method 2.

[0095] Furthermore, if missing points are scattered and it is difficult to extract intervals that satisfy the conditions of both shortening method 1 and shortening method 2, if data of 80 seconds or more can be obtained by stitching together intermittent normal RRI data, the accuracy will be close to that of shortening method 1. This method, that is, a method of extracting data of intervals of 80 seconds or more by stitching together multiple consecutive intervals of good data of less than 30 seconds, will be called shortening method 3.

[0096] Even if the total time length of good data is the same, the reliability decreases gradually in the following order: when shortening method 1 can be applied, when shortening method 2 cannot be applied but shortening method 1 cannot be applied, and when shortening method 3 cannot be applied but shortening method 1 cannot be applied (i.e., when shortening method 1 can be applied, the reliability is highest). The confidence interval extraction unit 34 considers the occurrence of missing data and the amount of available data, multiplies the reliability weight corresponding to the applied shortening method by the total time of the extracted confidence intervals, and divides that value by the time of the analysis window width to calculate a reliability score representing the reliability of the analysis interval. The reliability weight value is largest for shortening method 1 and smallest for shortening method 3. For example, the reliability weights for shortening methods 1, 2, and 3 may be 1.0, 0.9, and 0.8, respectively, but other values ​​may also be used.

[0097] The ANF index calculation unit 23 calculates the ANF index using the confidence interval data extracted by the shortening method with the highest reliability score (step 312 in Figure 3). The processing from step 312 onward is as described with reference to Figure 3.

[0098] Figure 10 is an explanatory diagram showing an example of the display of the evaluation results for the current time by the rapid response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0099] In this embodiment, the display mode can be selected from the current time and time series. Figure 10 shows an example when the current time is selected.

[0100] The basic information display unit 1001 displays the user ID, vehicle ID, heart rate sensor data, current work status, and a stress level comprehensively evaluated based on multivariate ANF indices as basic data for the displayed target. It also displays the reliability score for the interval of the analysis data acquired at the current time. Furthermore, it displays information regarding data correction processing, including whether past ANF indices were referenced, the reference time when doing so, whether LP (Low Performance) was applied, and whether interpolation processing was performed.

[0101] The graph display unit 1002 displays the current time and the most recent overall stress and relaxation level.

[0102] In the settings change unit 1003, the basic settings can be changed by performing operations such as changing the user ID setting based on input settings, changing sensors, changing business information, changing ANF index reference, changing reference time, changing noise reduction method, changing interpolation method, etc.

[0103] Clicking on "Display ANF Index List 1004" will show a table listing the values ​​of the multivariate ANF index at the current time. Although not shown in Figure 10, the information in the table shown in Figure 6B may also be displayed.

[0104] Clicking on graph display item 1005 allows you to specify individual ANF indicators in addition to the overall stress level, displaying the current time and recent trend of change for each specified ANF indicator.

[0105] Figure 11 is an explanatory diagram showing an example of the display of time-series evaluation results by the rapid-response autonomic nervous system function evaluation system 1 according to an embodiment of the present invention.

[0106] This example shows a time-series display on a daily basis. When time-series is selected as the display mode, information like that shown in Figure 11 will be displayed.

[0107] The basic information display unit 1101 is almost identical to the basic information display unit 1001 in the current time display mode. However, the basic information display unit 1101 displays the stress level as an average value over a predetermined relatively long period (e.g., one day).

[0108] The setting change 1102, ANF index list display 1103, and graph display item specification 1104 are the same as the setting change unit 1003, ANF index list display 1004, and graph display item specification 1005 in the current time display mode, respectively.

[0109] The graph display unit 1105 displays the trend of autonomic nervous system function indicators over a predetermined period (for example, one day).

[0110] In addition, the operational status 1106 in the time series, such as operation, loading, unloading, rest, and breaks, is also displayed. Furthermore, based on the reliability score of the data acquired in predetermined short time units, the reliability level 1107 of the acquired data in the time series and the ANF index calculated based on it are displayed.

[0111] By positioning cursor 1108 over a point on the graph, you can also view detailed information for the time corresponding to that point. While the detailed information is omitted in Figure 11, for example, the information from the table shown in Figure 6B for the corresponding time could be displayed.

[0112] Furthermore, the system of the embodiment of the present invention may be configured as follows.

[0113] (1) An autonomic nervous system function evaluation system comprising a processor (e.g., processor 2) and a memory device (e.g., at least one of memory 3 and storage device 4), wherein the memory device holds biological data measured over a predetermined period of time (e.g., BBI data) and autonomic nervous system function indices calculated based on biological data measured before a predetermined period of time (e.g., ANF indices included in the ANF index integrated DB 48), and the processor determines the validity of the biological data measured over a predetermined period of time based on the biological data measured over a predetermined period of time and the autonomic nervous system function indices calculated based on biological data measured before a predetermined period of time (e.g., step 308), and calculates autonomic nervous system function indices based on the data from the biological data measured over a predetermined period of time that is determined to be valid (e.g., step 312).

[0114] This allows for the dynamic calculation of ANF indices based on biometric data, such as heart rate interval data measured from wearable sensors worn during work, to be stored in an integrated ANF index database. By extracting reference ANF indices, the validity of biometric data acquired in a short time can be appropriately determined, enabling autonomic nervous system function evaluation that considers wearability, responsiveness, and reliability.

[0115] (2) In (1) above, the biometric data is heart rate interval data (e.g., BBI data), and the processor determines the validity of the heart rate interval data measured over a predetermined period of time based on the Lorentz plot of the heart rate interval measured over a predetermined period of time.

[0116] This allows for a proper assessment of the validity of heart rate interval data.

[0117] (3) In (2) above, the processor determines that heart rate interval data within the range of an elliptical region (e.g., ellipse 802) set on the Lorentz plot of heart rate intervals measured over a predetermined length of time is valid, calculates the center of the elliptical region based on the mean or median of heart rate intervals measured over a predetermined length of time and the mean or median of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined length of time (e.g., formula (3)), and calculates the diameter of the elliptical region based on the standard deviation on the Lorentz plot of heart rate intervals measured over a predetermined length of time and the standard deviation on the Lorentz plot of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined length of time (e.g., formulas (4), (5)).

[0118] In other words, by virtually setting an elliptical region on the Lorentz plot, drawing this elliptical region based on the concentration of biological data, and determining that the heart rate interval data within that range is valid, it is possible to appropriately set the validity range of heart rate interval data even for biological data acquired in a short period of time.

[0119] (4) In (3) above, the processor calculates the center of the elliptic region as the weighted average of the average or median of heart rate intervals measured over a predetermined length of time and the average or median of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined length of time (for example, formula (3)). The processor then calculates the diameter of the elliptic region as the value obtained by multiplying the weighted average of the standard deviation on the Lorentz plot of heart rate intervals measured over a predetermined length of time and the standard deviation on the Lorentz plot of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined length of time by a predetermined coefficient (for example, 2) (for example, formulas (4), (5)).

[0120] This makes it possible to appropriately set the validity range for heart rate interval data, even for biometric data acquired in a short period of time.

[0121] (5) In (4) above, values ​​extracted from autonomic nervous system function indices calculated based on more recent biological data are given greater weight.

[0122] This makes it possible to appropriately set the validity range for heart rate interval data, even for biometric data acquired in a short period of time.

[0123] (6) In (2) above, if the interval of data that is determined to be invalid based on the Lorentz plot from the heart rate interval data measured over a predetermined length of time is shorter than a predetermined standard, the processor interpolates the heart rate interval data for that interval based on the heart rate interval data before and after that interval (for example, step 310), and determines the data that is determined to be valid based on the Lorentz plot and the interpolated data to be good data.

[0124] This allows for the effective use of acquired data to perform reliable evaluations of autonomic nervous system indicators.

[0125] (7) In (6) above, the processor extracts confidence intervals from one or more intervals containing good data from the heart rate interval data measured over a predetermined length of time (e.g., step 311, Figure 9), and calculates a confidence score to evaluate the reliability of the confidence intervals based on at least one of the length of the interval containing good data and the sum of the lengths of multiple intervals containing good data (e.g., step 312).

[0126] This allows for the effective use of acquired data to perform reliable evaluations of autonomic nervous system indicators.

[0127] (8) In (7) above, the processor extracts confidence intervals from the intervals containing the good data based on at least one of the first extraction method, the second extraction method, and the third extraction method, wherein the first extraction method is a method of extracting one interval longer than a predetermined first consecutive interval length as a confidence interval, and the second extraction method is a method of extracting two or more intervals from the intervals containing the good data that are longer than a predetermined second consecutive interval length, and whose sum of lengths is longer than a predetermined third consecutive interval length as a confidence interval. The third extraction method involves extracting two or more intervals from among the intervals containing good data, where the sum of their lengths is longer than the length of the third consecutive interval, as confidence intervals. The length of the second consecutive interval is shorter than the length of the first consecutive interval, and the length of the third consecutive interval is longer than the length of the first consecutive interval. When the processor extracts confidence intervals using two or more of the first, second, and third extraction methods, it calculates an autonomic nervous system function index based on the heart rate interval data of the confidence interval with the highest reliability score among the two or more extracted confidence intervals.

[0128] This allows for the effective use of acquired data to perform reliable evaluations of autonomic nervous system indicators.

[0129] (9) In (8) above, the processor calculates a reliability score by multiplying the ratio of the length of the confidence interval to a predetermined length of time by a reliability weight corresponding to the confidence interval extraction method, with the reliability weight corresponding to the first extraction method being the largest and the reliability weight corresponding to the third extraction method being the smallest.

[0130] This allows for a proper evaluation of the reliability of the acquired data.

[0131] (10) In (2) above, the storage device holds information about the sensor that measured the biological data (e.g., sensor information 43), and the processor performs a formatting process on the biological data measured over a predetermined period of time according to the sensor (e.g., step 303), and determines the validity of the formatted biological data.

[0132] This allows for the appropriate generation of data used to evaluate autonomic nervous system indicators, depending on the type of sensor used.

[0133] (11) In (2) above, the processor associates the calculated autonomic nervous system function index with at least one of the following: the identification information of the person whose heart rate interval data is being measured, the age of the person, the gender of the person, the identification information of the vehicle the person is riding in, information indicating the content of the person's work, information regarding the sensor used to acquire the heart rate interval data, and the measurement time, and stores it in a memory device as integrated autonomic nervous system function index data (e.g., integrated ANF index DB48), and uses the autonomic nervous system function index (e.g., the index referenced in step 306) extracted from the integrated autonomic nervous system function index data based on specified extraction conditions to determine the validity of the biological data measured over a predetermined length of time.

[0134] This makes it possible to appropriately determine the validity of biometric data acquired in a short period of time.

[0135] (12) In (2) above, the heart rate interval data includes data on the interval of the R wave based on electrocardiogram measurements (for example, Figure 4A).

[0136] This allows us to obtain highly accurate heart rate interval data.

[0137] (13) In (2) above, the heart rate interval data includes data on the peak interval of the pulse wave measurement (for example, Figure 4B).

[0138] This reduces the burden on the person being measured during the measurement process.

[0139] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. For example, the embodiments described above are explained in detail for a better understanding of the present invention, and are not necessarily limited to those having all of the configurations described. Furthermore, it is possible to replace parts of the configuration of one embodiment with the configuration of another embodiment, and it is possible to add configurations from other embodiments to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with other configurations.

[0140] Furthermore, each of the above configurations, functions, processing units, and processing means may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. Alternatively, each of the above configurations and functions may be implemented in software by a processor interpreting and executing programs that implement each function. Information such as programs, tables, and files that implement each function can be stored in storage devices such as non-volatile semiconductor memory, hard disk drives, and SSDs (Solid State Drives), or in computer-readable non-temporary data storage media such as IC cards, SD cards, and DVDs.

[0141] Furthermore, the control lines and information lines shown are those deemed necessary for explanation purposes, and do not necessarily represent all control lines and information lines in the actual product. In practice, it can be assumed that almost all components are interconnected. [Explanation of Symbols]

[0142] 1. Rapid-response autonomic nervous system function assessment system 2 processors 3 memory 4. Storage devices 5 Input / Output Devices 6. Communication equipment 7 vehicles 11. Biosensors 19 Network 21 Heart rate interval acquisition unit 22 Correction Processing Unit 23 ANF index calculation section 24 Data Integration Department 25 Evaluation Result Display Section 26. Settings Section 31 Reference ANF index extraction part 32 Validity judgment part 33. Noise Reduction / Interpolation Processing Unit 34. Confidence interval extraction unit 41 Heart rate sensor measurement data 42 User Information 43 Sensor Information 44 Business Information 45 In-vehicle information 46 Short-term BBI data 47 ANF Index Data 48 ANF index integrated DB

Claims

1. An autonomic nervous system function evaluation system, It has a processor and a memory device, The memory device stores biological data measured over a predetermined period of time and autonomic nervous system function indices calculated based on biological data measured before the predetermined period of time. The aforementioned processor, Based on the biological data measured over the predetermined length of time and the autonomic nervous system function index calculated based on the biological data measured before the predetermined length of time, the validity of the biological data measured over the predetermined length of time is determined. Based on the data deemed valid from the biological data measured over the predetermined length of time, an autonomic nervous system function index is calculated. The calculated autonomic nervous system function index is associated with at least one of the following: the identification information of the person whose biological data is being measured, the person's age, the person's gender, the identification information of the vehicle the person is riding in, information indicating the person's occupation, information regarding the sensor used to acquire the biological data, and the measurement time, and stored in the storage device as integrated autonomic nervous system function index data. The autonomic nervous system function index extracted from the integrated autonomic nervous system function index data based on specified extraction conditions is used to determine the validity of the biological data measured over a predetermined period of time. The autonomic nervous system function evaluation system is characterized in that the extraction conditions are conditions relating to the identification information, state, or attributes of the person.

2. The autonomic nervous system function evaluation system according to claim 1, The extraction conditions mentioned above are conditions relating to the identification information of the person, The autonomic nervous system function evaluation system is characterized in that the processor extracts the autonomic nervous system function indicators of the same person as the person being analyzed from the integrated autonomic nervous system function indicator data, and uses the extracted autonomic nervous system function indicators to determine the validity of the biological data of the person being analyzed measured over a predetermined period of time.

3. The autonomic nervous system function evaluation system according to claim 1, The aforementioned extraction conditions are conditions relating to the state of the person, The autonomic nervous system function evaluation system is characterized in that the processor extracts the autonomic nervous system function indicators of a person in the same work state as the person being analyzed, or a person in a resting state, from the integrated autonomic nervous system function indicator data, and uses the extracted autonomic nervous system function indicators to determine the validity of the biological data of the person being analyzed measured over a predetermined period of time.

4. The autonomic nervous system function evaluation system according to claim 1, The extraction conditions mentioned above are conditions relating to the attributes of the person, The autonomic nervous system function evaluation system is characterized in that the processor extracts the autonomic nervous system function indicators of individuals with similar attributes to the person being analyzed from the integrated autonomic nervous system function indicator data, and uses the extracted autonomic nervous system function indicators to determine the validity of the biological data of the person being analyzed measured over a predetermined period of time.

5. The autonomic nervous system function evaluation system according to claim 4, The aforementioned attribute is the age or gender of the person. The autonomic nervous system function evaluation system is characterized in that the processor extracts the autonomic nervous system function indicators of a person of similar age to the person being analyzed, or a person of the same gender as the person being analyzed, from the integrated autonomic nervous system function indicator data, and uses the extracted autonomic nervous system function indicators to determine the validity of the biological data of the person being analyzed measured over a predetermined period of time.

6. The autonomic nervous system function evaluation system according to claim 1, The aforementioned biological data is heart rate interval data. The autonomic nervous system function evaluation system is characterized in that the processor determines the validity of the heart rate interval data measured over a predetermined period of time based on a Lorentz plot of the heart rate interval measured over a predetermined period of time.

7. The autonomic nervous system function evaluation system according to claim 6, The aforementioned processor, The heart rate interval data within the range of the elliptical region set on the Lorentz plot of heart rate intervals measured over the predetermined length of time is determined to be valid. The center of the elliptical region is calculated based on the average or median heart rate interval measured over a predetermined period of time, and the average or median heart rate interval among autonomic nervous system function indices calculated based on biological data measured before the predetermined period of time. An autonomic nervous system function evaluation system characterized by calculating the diameter of the elliptical region based on the standard deviation on the Lorentz plot of heart rate intervals measured over a predetermined period of time, and the standard deviation on the Lorentz plot of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined period of time.

8. The autonomic nervous system function evaluation system according to claim 7, The aforementioned processor, The center of the elliptical region is calculated by weighting the average or median heart rate interval measured over a predetermined period of time and the average or median heart rate interval among autonomic nervous system function indices calculated based on biological data measured before the predetermined period of time. An autonomic nervous system function evaluation system characterized by calculating the diameter of the elliptical region as a value obtained by multiplying a predetermined coefficient by the weighted average of the standard deviation on the Lorentz plot of heart rate intervals measured over a predetermined length of time and the standard deviation on the Lorentz plot of heart rate intervals among autonomic nervous system function indices calculated based on biological data measured before the predetermined length of time.

9. The autonomic nervous system function evaluation system according to claim 8, An autonomic nervous system function evaluation system characterized by assigning greater weight to values ​​extracted from autonomic nervous system function indices calculated based on more recent biological data.

10. The autonomic nervous system function evaluation system according to claim 6, The aforementioned processor, If, among the heart rate interval data measured over the predetermined length of time, an interval of data determined to be invalid based on the Lorentz plot is shorter than a predetermined standard, the heart rate interval data for that interval is interpolated based on the heart rate interval data before and after that interval. An autonomic nervous system function evaluation system characterized by determining data that is deemed valid based on the Lorentz plot and the interpolated data as good data.

11. An autonomic nervous system function evaluation system according to claim 10, The aforementioned processor, From the heart rate interval data measured over the predetermined length of time, a confidence interval is extracted from one or more consecutive intervals containing the good data. An autonomic nervous system function evaluation system characterized by calculating a reliability score for evaluating the reliability of the confidence interval based on at least one of the length of the interval in which the good data is continuous, and the sum of the lengths of multiple intervals in which the good data is continuous.

12. The autonomic nervous system function evaluation system according to claim 11, The processor extracts the confidence interval from the interval in which the good data is continuous, based on at least one of the first extraction method, the second extraction method, and the third extraction method. The first extraction method is a method of extracting one interval longer than a predetermined first continuous interval length as the confidence interval, The second extraction method is a method of extracting two or more sections from among the sections in which the good data is continuous, where the length of these sections is longer than a predetermined second continuous section length, and the sum of their lengths is longer than a predetermined third continuous section length, as the confidence interval. The third extraction method is a method of extracting two or more intervals from among the intervals in which the good data are continuous, the intervals whose total length is longer than the length of the third continuous interval, as the confidence intervals. The length of the second continuous section is shorter than the length of the first continuous section. The length of the third continuous section is longer than the length of the first continuous section. The autonomic nervous system function evaluation system is characterized in that, when the processor extracts the confidence intervals using two or more extraction methods from the first extraction method, the second extraction method, and the third extraction method, it calculates the autonomic nervous system function index based on the heart rate interval data of the confidence interval with the highest reliability score among the two or more extracted confidence intervals.

13. The autonomic nervous system function evaluation system according to claim 12, The processor calculates the reliability score by multiplying the ratio of the length of the confidence interval to the predetermined length of time by a reliability weight corresponding to the method of extracting the confidence interval. An autonomic nervous system function evaluation system characterized in that the reliability weight corresponding to the first extraction method is the largest, and the reliability weight corresponding to the third extraction method is the smallest.

14. The autonomic nervous system function evaluation system according to claim 6, The storage device holds information about the sensor that measured the biological data, The autonomic nervous system function evaluation system is characterized in that the processor performs a formatting process on biological data measured over a predetermined period of time according to the sensor, and determines the validity of the formatted biological data.

15. The autonomic nervous system function evaluation system according to claim 6, The autonomic nervous system function evaluation system is characterized in that the heart rate interval data includes data on the interval of the R wave based on electrocardiogram measurements.

16. The autonomic nervous system function evaluation system according to claim 6, The autonomic nervous system function evaluation system is characterized in that the heart rate interval data includes data on the peak interval of measured pulse waves.

17. An autonomic nervous system function evaluation method performed by an autonomic nervous system function evaluation system, The autonomic nervous system function evaluation system comprises a processor and a memory device. The memory device stores biological data measured over a predetermined period of time and autonomic nervous system function indices calculated based on biological data measured before the predetermined period of time. The aforementioned autonomic nervous system function evaluation method is: The processor provides a procedure for determining the validity of the biological data measured over a predetermined period of time, based on the biological data measured over a predetermined period of time and an autonomic nervous system function index calculated based on the biological data measured before the predetermined period of time. The processor performs a procedure to calculate an autonomic nervous system function index based on data that is determined to be valid from among the biological data measured over a predetermined period of time. The processor includes a procedure for storing the calculated autonomic nervous system function index in the storage device as integrated autonomic nervous system function index data, associating it with at least one of the following: identification information of the person whose biological data is being measured, the person's age, the person's gender, identification information of the vehicle the person is riding in, information indicating the person's occupation, information regarding the sensor used to acquire the biological data, and the measurement time. The processor uses the autonomic nervous system function index extracted from the integrated autonomic nervous system function index data based on specified extraction conditions to determine the validity of the biological data measured over a predetermined period of time. The method for evaluating autonomic nervous system function is characterized in that the extraction conditions are conditions relating to the identification information, state, or attributes of the person.

Images