Apparatus for providing health information service for mobile user and apparatus for providing health information service for passenger

Abstract

A health information service provision device (10) for a mobile user is provided with: a sensor (12) for acquiring a biological signal (BS) of the mobile user; an estimation unit (13) that estimates a heartbeat signal (HS) relating to the heartbeat of the mobile user; a calculation unit (14) that calculates VLF data (VD) relating to the extremely low frequency component; a state estimation unit (17) that estimates a change in the state of health of the mobile user on the basis of the difference between the current VLF data for the current mobile user and past VLF data (VDB) for a specific period of time that is past than the current VLF data; and a user interface (18) that provides a specific service to the mobile user on the basis of a change in the state of health of the mobile user.

Description

Technical Field

[0001] The present disclosure relates to a health information service providing device for a mobile body user and a health information service providing device for a passenger. Background Art

[0002] Conventionally, as an index indicating a person's health condition, the person's heartbeat or pulse is measured, and the ultra-low frequency component (VLF: Very Low Frequency) calculated from the measured value is used. The ultra-low frequency component (hereinafter referred to as VLF) is affected by physical conditions such as fatigue and stress, and thus is prone to short-term fluctuations. Therefore, in a medical institution, in order to obtain accurate information related to VLF, the heartbeat or pulse of a subject in a quiet state is measured. In other words, by measuring the heartbeat or pulse of a subject in a quiet state, the state of the subject is accurately grasped in an environment with less influence of interference, and the value of VLF is obtained. In Patent Document 1, a technique is described in which, as an example of a quiet state, the heartbeat or pulse of a subject in a sleeping state is measured in order to obtain stable information related to VLF.

[0003] In addition, the following technique has been conventionally disclosed: Regarding the drowsiness of a passenger of a mobile body exemplified by a vehicle, based on the temporal change in the heartbeat interval of the passenger and a determination criterion for the temporal change in a predetermined heartbeat interval, the drowsiness of the passenger is detected within a relatively short time (see Patent Document 2). In the above technique, a service is provided that reports a message corresponding to drowsiness to the passenger of the mobile body through an image or sound.

[0004] Prior Art Documents

[0005] Patent Documents

[0006] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2022-54332

[0007] Patent Document 2: Japanese Unexamined Patent Application Publication No. 2018-192128 Summary of the Invention

[0008] Problems to be Solved by the Invention

[0009] However, it is preferable to easily measure information related to VLF in a part of the actions that a subject performs in daily life, rather than measuring in such a limited state where the subject is in a quiet state or in a special device for reducing the influence of interference, because it is easy to grasp the health state of the subject.

[0010] Therefore, consider obtaining changes in the body movements of a mobile body user riding on a mobile body through sensors, estimating the heartbeat or pulse based on these changes in body movements, and calculating a value related to the VLF measured at rest (hereinafter referred to as VLF data) based on the estimated heartbeat or pulse.

[0011] However, the driving conditions of the mobile body change constantly. For example, when driving in a residential area with many narrow and winding roads, when driving on a street with a lot of people, when driving on a highway, etc., the mental state of the mobile body user also changes. Thus, as the driving conditions of the mobile body change, the information related to the heartbeat or pulse of the mobile body user also changes. Therefore, there is a problem that it is difficult to estimate the health status of the mobile body rider only based on the data during the limited period when riding on the mobile body.

[0012] In addition, in the case where the drowsiness of the rider increases, it is sometimes affected by the past living state of the rider. For example, imagine a situation where the rider has been in a state of continuous sleep deprivation or has accumulated physical fatigue in the past few days. In such a case, it is considered that even in a state where drowsiness is not detected, the possibility of the rider's increasing drowsiness is high. Therefore, it is desired to improve the accuracy of judging whether the drowsiness of the rider is on an increasing trend based on the past data of the rider related to drowsiness.

[0013] In view of such a background, the present disclosure aims to provide a health information service providing device for a mobile body user or a health information service providing device for a rider that solves any of the above problems.

[0014] Means for Solving the Problem

[0015] One aspect of the present disclosure is a health information service providing device for a mobile body user, wherein,

[0016] The health information service providing device for a mobile body user includes:

[0017] An acquisition device that acquires a biological signal of a mobile body user riding on a mobile body;

[0018] An estimation unit that estimates a heartbeat signal related to the heartbeat of the mobile body user based on the biological signal;

[0019] A calculation unit that calculates VLF data related to an extremely low frequency component of 0.0033 to 0.04 Hz based on the heartbeat signal;

[0020] The current VLF data acquisition unit acquires current VLF data, which is the VLF data of the mobile body user in the current situation, where the "current" includes the current ride when currently on board or the most recent ride when not currently on board;

[0021] The past VLF data acquisition unit acquires past VLF data, which is a statistical representative value that is a representative value of the count or position of the VLF data within a specific period in the past compared to the "current";

[0022] The state estimation unit estimates a change in the health state of the mobile body user based on the difference between the current VLF data and the past VLF data; and

[0023] The service provision unit provides a specific service to the mobile body user based on the change in the health state of the mobile body user.

[0024] In addition, another aspect of the present disclosure is a device for providing a health information service for a passenger, where

[0025] The device for providing a health information service for a passenger includes:

[0026] An acquisition device that acquires a biological signal of a passenger when on board a mobile body;

[0027] An estimation unit that estimates a heartbeat signal related to the heartbeat of the passenger based on the biological signal;

[0028] A calculation unit that calculates drowsiness omen data based on the heartbeat signal, where the drowsiness omen data is data related to the drowsiness omen of the passenger and is the number of detections of the drowsiness omen per unit time measured within a predetermined measurement time or a related value of the number of detections;

[0029] The current drowsiness omen data acquisition unit acquires current drowsiness omen data, which is the drowsiness omen data of the passenger in the state of currently being on board the mobile body;

[0030] The past drowsiness omen data acquisition unit acquires past drowsiness omen data, which is the drowsiness omen data detected when the passenger was on board the mobile body in the past;

[0031] The state estimation unit estimates whether the drowsiness of the passenger has increased based on whether the current drowsiness omen data and the past drowsiness omen data satisfy a predetermined comparison condition; and

[0032] The service providing unit controls a providing device that provides a specific service to the passenger based on the presumption that the drowsiness of the passenger has increased.

[0033] Advantageous Effects of the Invention

[0034] According to one aspect of the present disclosure, by comparing the current VLF data during the current ride with the past VLF data during the past ride based on the VLF data obtained from the mobile body user riding in the mobile body, it is possible to presume a change in the health state of the mobile body user. Based on the change in the health state thus presumed, it is possible to provide a service related to the health state to the mobile body user.

[0035] In addition, according to other aspects of the present disclosure, by determining whether the current drowsiness omen data and the past drowsiness omen data satisfy a comparison condition, it is possible to presume whether the drowsiness of the passenger has increased, and thus it is possible to observe the change in the drowsiness of the passenger over time. Therefore, compared with the case of making a determination only based on the current information of the passenger, that is, the current drowsiness omen data, it is possible to improve the accuracy of presuming the change in the drowsiness of the passenger.

[0036] It should be noted that the reference numerals in parentheses described in the claims indicate the correspondence with the specific means described in the following embodiments, and do not limit the technical scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a block diagram showing a health information providing device according to Embodiment 1.1.

[0038] Figure 2 is a cross-sectional view of a seat equipped with a sensor according to Embodiment 1.1.

[0039] Figure 3 is a graph showing the correlation between the VLF data measured by the sensor and the VLF measured by the electrocardiograph.

[0040] Figure 4 is a graph showing the VLF data as a statistical representative value for various periods.

[0041] Figure 5 is a flowchart showing the main process of the health information providing device according to Embodiment 1.1.

[0042] Figure 6 is a flowchart showing the state estimation process 1 according to Embodiment 1.1.

[0043] Figure 7 is a flowchart showing the state estimation process 2 according to Embodiment 1.1.

[0044] Figure 8 It is a flowchart showing the state estimation process 3 of Embodiment 1.1.

[0045] Figure 9 It is a flowchart showing the state estimation process 4 of Embodiment 1.1.

[0046] Figure 10 It is a flowchart showing the state estimation process 5 of Embodiment 1.1.

[0047] Figure 11 It is a block diagram showing the health information service providing device of Embodiment 1.2.

[0048] Figure 12 It is a flowchart showing the state estimation process 6 of Embodiment 1.2.

[0049] Figure 13 It is a flowchart showing the pre - judgment process 1 of Embodiment 1.2.

[0050] Figure 14 It is a block diagram showing the health information service providing device of Embodiment 1.3.

[0051] Figure 15 It is a flowchart showing the state estimation process 7 of Embodiment 1.3.

[0052] Figure 16 It is a flowchart showing the state estimation process 8 of Embodiment 1.4.

[0053] Figure 17 It is a block diagram showing the health information service providing device of Embodiment 1.5.

[0054] Figure 18 It is a flowchart showing the state estimation process 9 of Embodiment 1.5.

[0055] Figure 19 It is a flowchart showing the state estimation process 10 of Embodiment 1.6.

[0056] Figure 20 It is a block diagram showing the health information service providing device of Embodiment 1.7.

[0057] Figure 21 It is a flowchart showing the state estimation process 11 of Embodiment 1.7.

[0058] Figure 22 It is a block diagram showing the health information service providing device of Embodiment 1.8.

[0059] Figure 23 It is a flowchart showing the state estimation process 12 of Embodiment 1.8.

[0060] Figure 24 It is a block diagram showing the health information service providing device of Embodiment 1.9.

[0061] Figure 25 It is a flowchart showing the state estimation process 13 of Embodiment 1.9.

[0062] Figure 26 It is a flowchart showing the pre-judgment process 2 of Embodiment 1.9.

[0063] Figure 27 It is a cross-sectional view showing the manner in which the sensor related to the other embodiment (1.2) is installed on the upper surface of the seat cushion surface.

[0064] Figure 28 It is a block diagram showing the health information service providing device related to the other embodiment (1.3).

[0065] Figure 29 It is a block diagram showing the health information service providing device related to the other embodiment (1.4).

[0066] Figure 30 It is a block diagram showing the health information service providing device related to the other embodiment (1.5).

[0067] Figure 31 It is a block diagram showing the health information service providing device related to the other embodiment (1.6).

[0068] Figure 32 It is a block diagram showing the health information service providing device related to the other embodiment (1.7).

[0069] Figure 33 It is a block diagram showing the health information service providing device related to the other embodiment (1.8).

[0070] Figure 34 It is a block diagram showing the health information service providing device related to the other embodiment (1.9).

[0071] Figure 35 It is a block diagram showing the health information service providing device related to the other embodiment (1.10).

[0072] Figure 36 It is a block diagram showing the drowsiness information service providing device of Embodiment 2.1.

[0073] Figure 37 It is a cross-sectional view showing the seat equipped with the sensor of Embodiment 2.1.

[0074] Figure 38 It is a graph showing the change over time of the heart rate interval related to the drowsiness omen data of Embodiment 2.1.

[0075] Figure 39 It is a flowchart of the main program of the drowsiness information service providing device according to Embodiment 2.1.

[0076] Figure 40 It is a flowchart showing the state estimation process 21 of Embodiment 2.1.

[0077] Figure 41 It is a block diagram showing the drowsiness information service providing device according to Embodiment 2.2.

[0078] Figure 42 It is a flowchart showing the state estimation process 22 of Embodiment 2.2.

[0079] Figure 43 It is a block diagram showing the drowsiness information service providing device according to Embodiment 2.3.

[0080] Figure 44 It is a flowchart showing the state estimation process 23 of Embodiment 2.3.

[0081] Figure 45 It is a block diagram showing the drowsiness information service providing device according to Embodiment 2.4.

[0082] Figure 46 It is a flowchart showing the state estimation process 24 of Embodiment 2.4.

[0083] Figure 47 It is a flowchart showing the state estimation process 25 of Embodiment 2.5.

[0084] Figure 48 It is a flowchart showing the state estimation process 26 of Embodiment 2.6.

[0085] Figure 49 It is a flowchart showing the state estimation process 27 of Embodiment 2.7.

[0086] Figure 50 It is a cross-sectional view of the seat related to the drowsiness information service providing device according to Other Embodiment (2.2).

[0087] Figure 51 It is a block diagram showing the drowsiness information service providing device according to Other Embodiment (2.3).

[0088] Figure 52 It is a block diagram showing the drowsiness information service providing device according to Other Embodiment (2.4).

[0089] Figure 53 It is a block diagram showing the drowsiness information service providing device according to Other Embodiment (2.5).

[0090] Figure 54 It is a block diagram of a drowsiness information service providing device for other method (2.6).

[0091] Figure 55 It is a block diagram of a drowsiness information service providing device for other method (2.7).

[0092] Figure 56 It is a block diagram of a drowsiness information service providing device for other method (2.8).

[0093] Figure 57 It is a block diagram of a drowsiness information service providing device for other method (2.9).

[0094] Figure 58 It is a block diagram of a drowsiness information service providing device for other method (2.10). Detailed implementation mode

[0095] (Implementation mode 1.1)

[0096] 1. Outline of the health information service providing device 10

[0097] Refer to Figure 1 , and the outline of the health information service providing device 10 in implementation mode 1.1 will be described. The health information service providing device 10 provides a health information service to a mobile body user according to changes in the health state of the mobile body user.

[0098] In this mode, the mobile body 11 refers to means of transportation such as passenger vehicles, freight vehicles, work vehicles, etc., trams, ships, airplanes, helicopters, and passenger drones that people ride on. The mobile body user in this mode includes a person who rides and drives the mobile body 11, a person who rides on an autonomously driven mobile body 11, or a person who rides on a mobile body 11 driven by others.

[0099] As Figure 1 shown, the health information service providing device 10 in this mode includes a sensor 12, an estimation unit 13, a calculation unit 14, a current VLF data acquisition unit 15, a past VLF data acquisition unit 16, a state estimation unit 17, and a user interface 18 (an example of a service providing unit).

[0100] The mobile body 11 includes a seat 21 for the mobile body user to sit on. The sensor 12 is installed on the seat 21. When the seat 21 is applied to the driver's seat, the seat 21 is used to detect the sitting state of the driver during driving and the biometric signal BS of the driver. When the seat 21 is applied to a seat different from the driver's seat, the seat 21 is used to detect the sitting state of the passenger of the mobile body 11 different from the driver and the biometric signal BS.

[0101] As shown Figure 2 in the figure, the seat 21 includes a frame portion 28, a cushion portion 29, and a sensor 12. The seat 21 of this embodiment includes a headrest 22c. However, the headrest 22c may be omitted.

[0102] The frame portion 28 includes a seat surface seat frame 31 and a back seat frame 41. The cushion portion 29 includes a seat surface seat cushion 30 mounted on the seat surface seat frame 31 and a back seat cushion 42 mounted on the back seat frame 41. The seat surface seat cushion 30 includes a first seat surface seat cushion 32 and a second seat surface seat cushion 35.

[0103] The seat surface seat frame 31 is formed of a rigid material such as metal or hard resin and is mounted on the vehicle. The seat surface seat frame 31 has a plate-like portion. The plate-like portion is mounted on the vehicle with the plate surface facing the vertical direction. The upper surface of the plate-like portion is formed as a mounting seat surface 31a for mounting the first seat surface seat cushion 32. The portion of the seat surface seat frame 31 different from the plate-like portion is formed into an arbitrary shape such as a rod shape or a column shape.

[0104] The first seat surface seat cushion 32 is formed of an elastic material such as foamed resin. The first seat surface seat cushion 32 is mounted in a state of being placed on the mounting seat surface 31a formed on the upper surface of the seat surface seat frame 31. The upper surface of the first seat surface seat cushion 32 is formed as a pressure-receiving surface 32a that receives pressure from the buttocks of the occupant. The lower surface of the first seat surface seat cushion 32, that is, the anti-pressure-receiving surface 32b on the back side of the pressure-receiving surface 32a, faces the mounting seat surface 31a of the seat surface seat frame 31.

[0105] The first seat surface seat cushion 32 has a storage recess 50 that opens downward toward the seat surface seat frame 31 on the anti-pressure-receiving surface 32b. The cross-sectional shape of the storage recess 50 can be set to an arbitrary shape such as a polygon, a circle, or an oval. The cross-sectional shape of the storage recess 50 in this embodiment is a quadrilateral. The portion of the storage recess 50 located on the side opposite to the direction in which the storage recess 50 opens is formed as the bottom 52 of the storage recess 50.

[0106] The second seat surface seat cushion 35 is received in the receiving recess 50. The second seat surface seat cushion 35 is mounted on the mounting seat surface 31a of the seat surface seat frame 31. The surface of the second seat surface seat cushion 35 that faces the mounting seat surface 31a of the seat surface seat frame 31 is formed as the mounting surface 35b. In a state where the first seat surface seat cushion 32 and the second seat surface seat cushion 35 are mounted on the seat surface seat frame 31, the pressure-receiving surface 32b of the first seat surface seat cushion 32 and the mounting surface 35b of the second seat surface seat cushion 35 are coplanar. Further, in a state where the first seat surface seat cushion 32 and the second seat surface seat cushion 35 are mounted on the seat surface seat frame 31, a gap is formed between the inner side surface of the receiving recess 50 and the outer side surface of the second seat surface seat cushion 35. The upper surface of the second seat surface seat cushion 35 (the surface on the side opposite to the seat surface seat frame 31) is formed as the second pressing surface 35a that presses the sensor 12 from below. However, it may also be configured such that the receiving recess 50 of the first seat surface seat cushion 32 opens upward, and the second seat surface seat cushion 35 is received in the receiving recess 50.

[0107] A seat surface skin member 33 covers the surface of the first seat surface seat cushion 32. The seat surface skin member 33 covers at least the pressure-receiving surface 32a of the first seat surface seat cushion 32. The seat surface skin member 33 is formed of a material that is less stretchable than the first seat surface seat cushion 32, such as cloth or leather.

[0108] The back seat frame 41 is formed of a hard material such as metal or hard resin, for example. The back seat frame 41 is formed in a plate shape, a rod shape, or the like. For example, when the seat body 22 is provided with a backrest adjustment function, the back seat frame 41 is swingably supported by the seat surface seat frame 31. Of course, the back seat frame 41 may also be integrally fixed to the seat surface seat frame 31.

[0109] The back seat cushion 42 is formed of an elastic material such as foamed resin. The back seat cushion 42 is laminated and mounted on the back seat frame 41. The surface of the back seat cushion 42 on the side opposite to the back seat frame 41 is formed as the surface that receives pressure from the back of the occupant. That is, the surface of the back seat cushion 42 that faces the back seat frame 41 is formed as the pressure-receiving surface 42b of the back seat cushion 42.

[0110] A back surface skin member 43 covers the surface of the back seat cushion 42. The back surface skin member 43 covers at least the pressure-receiving surface 42a of the back seat cushion 42. The back surface skin member 43 is formed of materials such as cloth or leather.

[0111] The headrest 22c is disposed at the upper end of the seat back portion 22b. The headrest 22c includes a cushion 45 and a skin member 46. Here, in Figure 2In this case, the first seat surface seat cushion 32 and the back seat cushion 42 are separated, but they may also be integrated. Additionally, the back seat cushion 42 and the headrest 22c are separated, but they may also be integrated.

[0112] The sensor 12 is disposed between the first pressing surface 52b formed in the receiving recess 50 of the first seat surface seat cushion 32 and the second pressing surface 35a of the second seat surface seat cushion 35. The first pressing surface 52b is provided on a convex portion 52a protruding downward. Here, when a passenger sits on the seat body 22, pressure is applied from the passenger's buttocks to the pressure receiving surface 32a of the first seat surface seat cushion 32, and this pressure is transmitted through the first seat surface seat cushion 32 to the first pressing surface 52b of the first seat surface seat cushion 32. Moreover, the sensor 12 receives pressure from the first pressing surface 52b of the first seat surface seat cushion 32. That is, the sensor 12 detects a physical quantity corresponding to the pressure transmitted through the first seat surface seat cushion 32 from the pressure receiving surface 32a of the first seat surface seat cushion 32 in the seated state of the passenger.

[0113] Here, the sensor 12 is disposed on the seat seat surface portion 22a, but it may also be disposed on the seat back surface portion 22b. In this case, the sensor 12 is disposed between the back seat frame 41 and the back seat cushion 42. Moreover, in the seated state of the passenger, the sensor 12 detects a physical quantity corresponding to the pressure transmitted through the back seat cushion 42 from the pressure receiving surface 32a of the back seat cushion 42.

[0114] The sensor 12 is connected to a control circuit 55 for controlling the sensor 12. The control circuit 55 controls the operation of the sensor 12 and acquires the physical quantity detected by the sensor 12. The control circuit 55 detects the biological signal BS of the mobile body user based on the physical quantity acquired from the sensor 12. The control circuit 55 may also perform processing such as amplification and noise cancellation on the biological signal BS.

[0115] The sensor 12 and the control circuit 55 constitute a monitoring system 56 (an example of an acquisition device) for monitoring the biological signal BS of the mobile body user.

[0116] The control circuit 55 sends the biological signal BS to the ECU 57 (Electronic Control Unit). The ECU 57 includes an estimation unit 13 and a calculation unit 14.

[0117] The estimation unit 13 acquires the biological signal BS obtained from the control circuit 55 of the monitoring system 56. The biological signal BS is a superordinate concept of the heartbeat, body movement, respiration, etc. of the mobile body user. In addition, it also includes the case where signals such as heartbeat, body movement, and respiration are mixed. Pulse refers to the pulsation generated in the artery. On the other hand, heartbeat refers to the pulsation of the heart pumping blood to the whole body. In the case of a healthy person, usually the heartbeat and the pulse are consistent. Therefore, hereinafter, the heartbeat and the pulse will be collectively referred to as the heartbeat signal HS related to the heartbeat. The estimation unit 13 estimates the heartbeat signal HS related to the heartbeat of the mobile body user based on the biological signal BS.

[0118] The calculation unit 14 calculates the VLF data VD related to the very low frequency component of 0.0033 Hz to 0.04 Hz. As described above, conventionally, in medical institutions, VLF has been used as an index indicating a person's health status. This VLF is calculated based on the electrocardiogram measured by an electrocardiograph worn on a person. In the electrocardiogram obtained from the electrocardiogram, the peaks of the heartbeat clearly appear. Therefore, the VLF can be calculated based on these peaks.

[0119] However, the sensor 12 of this method is subjected to the pressure of the buttocks of the mobile body user sitting on the seat 21, detects the biological signal BS based on this pressure, and estimates the heartbeat signal HS based on this biological signal BS. Therefore, strictly speaking, the data related to the very low frequency component obtained based on the heartbeat signal HS of this method is different from the VLF obtained from the electrocardiogram. Therefore, hereinafter, the data related to the very low frequency component obtained based on the heartbeat signal HS of this method is distinguished from the VLF obtained from the electrocardiogram, and is called VLF data VD.

[0120] As Figure 3 shown, it can be seen that the VLF data VD related to this method has a high correlation with the VLF obtained from the electrocardiogram. In this way, the VLF data VD obtained from the mobile body user sitting on the seat 21 can be used to estimate the change in the health status of the mobile body user.

[0121] The calculation unit 14 sends the VLF data VD to the user interface 18. As the user interface 18, examples include a car navigation system, a smart phone, a tablet terminal, a smart watch, etc. In this method, a car navigation system installed in the mobile body 11 is adopted.

[0122] The user interface 18 includes both or one of a screen display device and a speaker for providing a specific service to the mobile body user. The user interface 18 provides a specific service to the mobile body user through images or sounds.

[0123] The user interface 18 is equipped with a communication device (not shown), and is connected to a network 58 such as the Internet through this communication device. The user interface 18 transmits and receives data to and from the cloud 59 via the network 58.

[0124] The cloud 59 is equipped with the current VLF data acquisition unit 15, the past VLF data acquisition unit 16, the state estimation unit 17, and the storage unit 60.

[0125] The current VLF data acquisition unit 15 acquires the current VLF data VDA from the user interface 18 via the network 58. When the mobile body user is currently riding on the mobile body 11, the current VLF data VDA is the VLF data VD of the current mobile body user during the current ride. When the mobile body user is not currently riding on the mobile body 11, the current VLF data VDA is the VLF data VD of the mobile body user including the most recent ride.

[0126] When the mobile body user is currently riding on the mobile body 11, the statistical representative value of the VLF data VD during at least a part of the current ride period is used as the current VLF data VDA. Additionally, when the mobile body user is not currently riding on the mobile body 11, the statistical representative value of the VLF data VD during at least a part of the most recent ride period is used as the current VLF data VDA.

[0127] The VLF data VD sent from the user interface 18 to the cloud 59 via the network 58 is acquired by the current VLF data acquisition unit 15 and sequentially saved as the past VLF data VDB in the storage unit 60.

[0128] The past VLF data acquisition unit 16 acquires the past VLF data VDB saved in the storage unit 60. The past VLF data VDB is the statistical representative value of the VLF data VD during a specific past period. The statistical representative value includes a count representative value or a position representative value.

[0129] The statistical representative value refers to a characteristic value that numerically summarizes the main trend of the frequency distribution when calculating statistical data. The statistical representative value is a value that represents the information contained in a set of data with a single numerical value, and there are two types: the count representative value and the position representative value.

[0130] The count representative value is also called the mathematical representative value and is classified into the arithmetic mean, geometric mean, harmonic mean, quadratic mean, etc. The arithmetic mean is also called the additive mean and is the value obtained by dividing the sum of the data by the number of data. The geometric mean is also called the multiplicative mean and is the Nth root of the product of each data. The harmonic mean is the reciprocal of the arithmetic mean of the reciprocals of each data. The quadratic mean is the square root of the arithmetic mean of the values obtained by squaring the data.

[0131] The position representative values are subdivided into median, mode, quantiles, etc. They regard one or a few data occupying specific positions in the frequency distribution as representative values of all the data. The median is the value exactly in the middle when the measured values are arranged in ascending order. The mode refers to the value that exists the most and appears most frequently in a set of data. The quantile value, based on the same concept as the median, refers to the values separated at points such as quartiles, quintiles, deciles, and percentiles. For example, the quartiles refer to the values of the data at 1 / 4, 2 / 4, and 3 / 4 of the entire data column arranged in ascending order, which are called the first quartile, the second quartile, and the third quartile, respectively.

[0132] The state estimation unit 17 estimates the change in the health state of the mobile body user based on the difference between the current VLF data VDA and the past VLF data VDB.

[0133] The storage unit 60 stores the past VLF data VDB sent from the user interface 18 via the network 58. In addition, the storage unit 60 stores the threshold value TVA, the same - period threshold value TVB, and the period threshold value TVC.

[0134] 2. Regarding the VLF data VD

[0135] 2.1. Regarding the statistical representative values

[0136] Next, with reference to Figure 4 the VLF data VD will be described. When the mobile body rider rides on the mobile body 11 and sits on the seat 21, the monitoring system 56 (sensor 12 and control circuit 55) acquires the biological signal BS of the mobile body rider. Based on the biological signal BS, the estimation unit 13 estimates the heartbeat signal HS, and the calculation unit 14 calculates the VLF data VD. The VLF data VD is calculated as a statistical representative value related to the very - low - frequency component within a predetermined period. In this application, the VLF data VD is calculated as the arithmetic mean of the time of the data related to the very - low - frequency component within a predetermined period.

[0137] Figure 4 In (a) of

[0138] Figure 4 the results obtained by measuring the VLF data VD of the mobile body user within two days are shown. The vertical axis represents the intensity of the VLF data VD. The larger the VLF data VD, the better the health state of the mobile body user can be judged. On the other hand, when the VLF data VD becomes smaller, it can be judged that the health state of the mobile body user is not good. The horizontal axis represents the elapsed time.

[0139] In Figure 4 in (a), the four bar graphs marked with the reference numeral "p" are the VLF data VD when the moving body user rides on the moving body 11 in the morning of the first day. At this time, the moving body user rides on the moving body 11 for a time period equal to the amount of four shortest periods.

[0140] The two bar graphs marked with the reference numeral "q" are the VLF data VD when the moving body user rides on the moving body 11 in the afternoon of the first day. At this time, the moving body user rides on the moving body 11 for a time period equal to the amount of two shortest periods.

[0141] The four bar graphs marked with the reference numeral "r" are the VLF data VD when the moving body user rides on the moving body 11 in the morning of the second day during measurement. At this time, the moving body user rides on the moving body 11 for a time period equal to the amount of four shortest periods.

[0142] The time period in which the VLF data VD of the second day marked with the reference numeral "r" is measured is substantially the same as the time period in which the VLF data VD of the first day marked with the reference numeral "p" is measured. In other words, the time period in which the VLF data VD of the second day marked with the reference numeral "r" is measured includes the same time as the time when the VLF data VD of the first day marked with the reference numeral "p" is measured.

[0143] The two bar graphs marked with the reference numeral "s" are the VLF data VD when the moving body user rides on the moving body 11 in the afternoon of the second day during measurement. At this time, the moving body user rides on the moving body 11 for a time period equal to the amount of three shortest periods.

[0144] The time period in which the VLF data VD of the second day marked with the reference numeral "s" is measured is substantially the same as the time period in which the VLF data VD of the first day marked with the reference numeral "q" is measured. In other words, the time period in which the VLF data VD of the second day marked with the reference numeral "s" is measured includes the same time as the time when the VLF data VD of the first day marked with the reference numeral "q" is measured.

[0145] In Figure 4 in (b), one bar graph is the average value of the VLF data VD for one day. Figure 4 The leftmost bar graph in (b) in is Figure 4 the daily average of the VLF data VD of the first day in (a). Figure 4 The second bar graph from the left in (b) is Figure 4 the daily average of the VLF data VD of the second day in (a). Hereinafter, in Figure 4 in (b), the daily averages of the VLF for the third day and the fourth day are recorded in order from the left. In Figure 4In (b) thereof, the dotted line indicates the division of a week. In Figure 4 In (b) thereof, the change of the VLF data VD from the start of measuring the health state of the mobile body user to the seventh week is shown.

[0146] In Figure 4 In (c) thereof, one bar graph is the average value of the VLF data VD for one week. Figure 4 In (c) thereof, the leftmost bar graph is Figure 4 the weekly average of the VLF data VD for the first week in (b) thereof. Figure 4 In (c) thereof, the second bar graph from the left is Figure 4 the weekly average of the VLF data VD for the second week in (b) thereof. Hereinafter, in Figure 4 In (c) thereof, the daily averages of the VLF for the third week and the fourth week are successively recorded from the left. In Figure 4 In (c) thereof, the change of the VLF data VD from the start of measuring the health state of the mobile body user to the eleventh month is shown. It should be noted that the division of weeks and the division of months are not necessarily consistent. Therefore, the division of months is not shown in Figure 4 In (c) thereof.

[0147] In Figure 4 In (d) thereof, one bar graph is the average value of the VLF data VD within one month. Figure 4 In (d) thereof, the leftmost bar graph is Figure 4 the monthly average of the VLF data VD for the first month in (c) thereof. Figure 4 In (d) thereof, the second bar graph from the left is Figure 4 the monthly average of the VLF data VD for the second month in (c) thereof. Hereinafter, in Figure 4 In (d) thereof, the monthly averages of the VLF for the third month and the fourth month are successively recorded from the left. In Figure 4 In (d) thereof, the dotted line indicates the division of the first year and the second year. In Figure 4 In (d) thereof, the change of the VLF data VD from the start of measuring the health state of the mobile body user to the second year is shown.

[0148] 2.2. Regarding relative comparison

[0149] As Figure 4 shown in (a) thereof, in this mode, it is configured to obtain the VLF data VD when the mobile body user rides on the mobile body 11. Thus, in daily life, the VLF data VD is obtained under relatively similar conditions. By relatively comparing a plurality of VLF data VD obtained under such relatively similar conditions with each other, the change in the health state of the mobile body rider can be inferred.

[0150] For example, in Figure 4 in (c), the bar graphs labeled with reference numerals "x", "y", and "z" are studied. As described above, in Figure 4 in (c), the weekly average VLF data VD is recorded. When the VLF data VD for the x-th week labeled with reference numeral "x" is compared with the VLF data VD for the y-th week labeled with reference numeral "y", the VLF data VD for the y-th week is larger than the VLF data VD for the x-th week. Thus, it is presumed that the health state of the mobile body user has changed in a better direction in the y-th week compared to the x-th week. On the other hand, the VLF data VD for the z-th week is smaller than the VLF data VD for the y-th week. Thus, it is presumed that the health state of the mobile body user has changed in a worse direction in the z-th week compared to the y-th week.

[0151] 3. Operations of the Embodiment

[0152] 3.1. Main Program

[0153] Next, with reference to Figure 5 , the operations of the health information service providing apparatus 10 of this embodiment will be described. Figure 5 FIG. shows a flowchart of the operations of the health information service providing apparatus 10 of this embodiment. When the health information service providing apparatus 10 is started, the biological signal acquisition process S1 is executed. In the biological signal acquisition process S1, the monitoring system 56 (sensor 12 and control circuit 55) acquires a biological signal BS from a mobile body user sitting on the seat 21 of the mobile body 11. The biological signal BS is transmitted to the control circuit 55.

[0154] Next, the heart rate signal estimation process S2 is executed. In the heart rate signal estimation process S2, the estimation unit 13 estimates a heart rate signal HS related to the heart rate of the mobile body user based on the biological signal BS acquired from the monitoring system 56.

[0155] Next, the VLF data calculation process S3 is executed. In the VLF data calculation process S3, the calculation unit 14 calculates VLF data VD based on the heart rate signal HS acquired from the estimation unit 13. The calculated VLF data VD is sent from the user interface 18 to the cloud 59 via the network 58.

[0156] Next, the state estimation process S4 is executed. In the state estimation process S4, the state estimation unit 17 estimates the change in the health state of the mobile body user based on the difference between the current VLF data VDA and the past VLF data VDB.

[0157] Next, service provision process S5 is executed. In service provision process S5, the service provision unit provides a specific service to the mobile body user based on the information related to the change in the health state of the mobile body user obtained from the state estimation unit 17.

[0158] When service provision process S5 ends, the operation of the health information service providing device 10 ends.

[0159] 3.2. State Estimation Process

[0160] Next, refer to Figures 6 - 10 , and the state estimation process S4 will be described. In this mode, as Figures 6 - 10 shows, the state estimation process S4 includes five processes: state estimation process 1 (S10) to state estimation process 5 (S50). All of state estimation process 1 (S10) to state estimation process 5 (S50) can be executed. Additionally, one or more selected from state estimation process 1 (S10) to state estimation process 5 (S50) can also be executed. In the case of selection from state estimation process 1 (S10) to state estimation process 5 (S50), the mobile body user can select one or more from the five processes. Additionally, it can also be configured to be pre-selected according to the specifications of the health information service providing device 10 or the sending location, etc. Hereinafter, state estimation process 1 (S10) to state estimation process 5 (S50) will be described. However, the state estimation process S4 can also be configured to include one to four or six or more state estimation processes.

[0161] (1) State Estimation Process 1

[0162] Figure 6 The flowchart showing state estimation process 1 (S10). The state estimation process 1 in this mode, as will be described in detail later, uses the threshold value TVA to judge the first past difference value ΔDVA, and also uses the threshold value TVA to judge the second past difference value ΔDVB.

[0163] When state estimation process 1 (S10) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11).

[0164] Next, the past VLF data acquisition unit 16 acquires the first past VLF data VDF from the storage unit 60 (S13). The first past VLF data VDF is the statistical representative value of the VLF data VD within a specific period earlier than the current acquisition of the VLF data VDA by more than once. As the statistical representative value, any statistical representative value such as the arithmetic mean of the VLF data VD during one ride, the daily average of the VLF data VD, the weekly average of the VLF data VD, the monthly average of the VLF data VD, etc. can be appropriately selected.

[0165] Next, the past VLF data acquisition unit 16 acquires second past VLF data VDG from the storage unit 60 (S13). The second past VLF data VDG is a statistical representative value of the VLF data VD within a specific period that is earlier than the period when the first past VLF data VDF was acquired by more than once. Similarly to the first past VLF data VDF, as the statistical representative value, any statistical representative value such as the arithmetic mean of the VLF data VD during one ride, the daily average of the VLF data VD, the weekly average of the VLF data VD, the monthly average of the VLF data VD, etc. can be appropriately selected. In this method, the period of the first past VLF data VDF and the period of the second past VLF data VDG are set to be the same. For example, if the first past VLF data VDF is the daily average, then the second past VLF data VDG is also set to the daily average.

[0166] Next, the state estimation unit 17 calculates a first past difference value ΔDVA obtained by subtracting the current VLF data VDA from the first past VLF data VDF (S14). That is, the state estimation unit 17 investigates how the health state of the current mobile body user has changed compared to the past health state. Next, the state estimation unit 17 determines whether the first past difference value ΔDVA is equal to or greater than a threshold value TVA stored in the storage unit 60 (S15). Here, the threshold value TVA is an example of a first comparison reference.

[0167] When the first past difference value ΔDVA is equal to or greater than the threshold value TVA (S15: Yes), it means that the VLF data VD related to the health state of the current mobile body user has decreased compared to the VLF data VD related to the past health state. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in a bad direction (S16). Thus, the state estimation process 1 (S10) ends.

[0168] On the other hand, when the first past difference value ΔDVA is less than the threshold value TVA (S15: No), the state estimation unit 17 calculates a second past difference value ΔDVB obtained by subtracting the current VLF data VDA from the second past VLF data VDG (S17). That is, the state estimation unit 17 investigates how the health state of the current mobile body user has changed compared to the health state further in the past than the period when the first past VLF data VDF was measured. Next, the state estimation unit 17 determines whether the second past difference value ΔDVB is equal to or greater than the threshold value TVA stored in the storage unit 60 (S18). Here, the threshold value TVA is an example of a second comparison reference.

[0169] When the second past difference value ΔDVB is equal to or greater than the threshold value TVA (S18: Yes), it means that the VLF data VD related to the current health state of the mobile body user is smaller than the VLF data VD related to the health state in the more distant past than the period when the first past VLF data VDF was measured. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in an unfavorable direction (S16). Thereby, the state estimation process 1 (S10) ends.

[0170] When the second past difference value ΔDVB is less than the threshold value TVA (S18: No), the state estimation process 1 (S10) ends.

[0171] (2) State estimation process 2

[0172] Figure 7 The flowchart showing the state estimation process 2 (S20). The state estimation process 2 (S20) of this mode is a method of comparing the current VLF data VDA for one ride with the past VLF data VDB for multiple past rides, as will be described in detail later. When executing the state estimation process 2 (S20), the current VLF data acquisition unit 15 acquires the current VLF data VDA for one ride at the current ride or the most recent ride (S21).

[0173] Next, the past VLF data acquisition unit 16 acquires the past VLF data VDB from the storage unit 60 (S22). The past VLF data VDB is a statistical representative value of the VLF data VD for multiple rides within a predetermined past period. As the statistical representative value, an arithmetic mean of the VLF data VD for multiple rides, a daily average of the VLF data VD, a weekly average of the VLF data VD, a monthly average of the VLF data VD, or other statistical representative values of multiple rides can be appropriately selected.

[0174] Next, the state estimation unit 17 calculates the difference value ΔDVC obtained by subtracting the current VLF data VDA from the past VLF data VDB (S23). That is, the state estimation unit 17 investigates how the current health state of the mobile body user has changed compared to the health state when the mobile body user has taken rides on the mobile body 11 multiple times in the past. Next, the state estimation unit 17 determines whether the difference value ΔDVC is equal to or greater than the threshold value TVA stored in the storage unit 60 (S24).

[0175] When the difference value ΔDVC is equal to or greater than the threshold value TVA (S24: Yes), it means that the current VLF data VDA related to the health state of the mobile body user has decreased compared to the past VLF data VDB related to the health state during multiple past rides on the mobile body 11. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in an unfavorable direction (S25). Thereby, the state estimation process 2 (S20) ends.

[0176] On the other hand, when the difference value ΔDVC is less than the threshold value TVA (S24: No), the state estimation process 2 (S20) ends.

[0177] (3) State estimation process 3

[0178] Figure 8 The flowchart showing the state estimation process 3 (S30). The state estimation process 3 (S30) of this method is, as described in detail later, a method of comparing the current VLF data VDA with the past VLF data VDB including the time point same as the time point when the current VLF data VDA is measured. When the state estimation process 3 (S30) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S31), and the current VLF data VDA is the VLF data VD during the current ride or the most recent ride.

[0179] Next, the past VLF data acquisition unit 16 acquires the past VLF data VDB (S32), and the past VLF data VDB is the statistical representative value of the VLF data VD during the past ride including the time point same as the time point when the current VLF data VDA is measured.

[0180] Next, the state estimation unit 17 calculates the same - time - period difference value ΔDVD obtained by subtracting the current VLF data VDA from the past VLF data VDB (S33). That is, the state estimation unit 17 investigates how the health state of the current mobile body user has changed compared to the health state of the past mobile body user during the same - time - period ride. Next, the state estimation unit 17 determines whether the same - time - period difference value ΔDVD is equal to or greater than the same - time - period threshold value TVB stored in the storage unit 60 (S34).

[0181] When the same - time - period difference value ΔDVD is equal to or greater than the same - time - period threshold value TVB (S34: Yes), it means that the current VLF data VDA related to the health state of the mobile body user has decreased compared to the past VLF data VDB related to the past health state during the same - time - period ride on the mobile body 11. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in an unfavorable direction (S35). Thereby, the state estimation process 3 (S30) ends.

[0182] On the other hand, when the difference value ΔDVD within the same time period is less than the threshold value TVB within the same time period (S34: No), the state estimation process 3 (S30) ends.

[0183] (4) State estimation process 4

[0184] Figure 9 The flowchart showing the state estimation process 4 (S40). The state estimation process 4 (S40) of this method is a method of comparing the current VLF data VDA and the past VLF data VDB within a predetermined comparison period when the mobile body user is on board the mobile body 11. When the state estimation process 4 (S40) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S41), and the current VLF data VDA is a statistical representative value of the VLF data VD within a predetermined comparison period including the current boarding time or the most recent boarding time. The comparison period can be appropriately selected, for example, for any number of boarding times, once or more than once, any period such as one day, one week, or one month.

[0185] Next, the past VLF data acquisition unit 16 acquires the past VLF data VDB (S42), and the past VLF data VDB is a statistical representative value when the VLF data VD within a comparison period earlier than the current boarding time or the most recent boarding time is acquired. The comparison period related to the past VLF data VDB can be the same as or different from the comparison period related to the current VLF data VDA.

[0186] Next, the state estimation unit 17 calculates the period difference value ΔDVE obtained by subtracting the current VLF data VDA from the past VLF data VDB (S43). That is, the state estimation unit 17 investigates how the health state of the current mobile body user within the comparison period has changed compared to the health state of the mobile body user within the past comparison period. Next, the state estimation unit 17 determines whether the period difference value ΔDVE is equal to or greater than the period threshold value TVC stored in the storage unit 60 (S44).

[0187] When the period difference value ΔDVE is equal to or greater than the period threshold value TVC (S44: Yes), it means that the current VLF data VDA related to the health state of the mobile body user within the comparison period is smaller than the past VLF data VDB related to the health state of the mobile body user within the past comparison period. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in a bad direction (S45). Thus, the state estimation process 4 (S40) ends.

[0188] On the other hand, when the period difference value ΔDVE is less than the threshold value TVB within the same time period (S44: No), the state estimation process 4 (S40) ends.

[0189] (5) State estimation process 5

[0190] Figure 10 The flowchart showing the state estimation process 5 (S50). The state estimation process 5 (S50) of this method will be described in detail later. It is a method of estimating the change in the health state of the mobile body user based on the trend of the VLF data VD from the past ride to the current ride. When the state estimation process 5 (S50) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S51).

[0191] Next, the past VLF data acquisition unit 16 acquires a plurality of past VLF data VDB (S52). From the perspective of the passage of time, the plurality of past VLF data VDB can be continuous or discrete.

[0192] As an example of being continuous, for example, it can be set to the past VLF data VDB for a continuous week traced back from the date when the current VLF data VDA is acquired, or it can be set to the past VLF data VDB for a month traced back from the date when the current VLF data VDA is acquired. The period of the acquired past VLF data VDB is arbitrary.

[0193] As an example of being discrete, for example, it can be set to a plurality of past VLF data VDB acquired on the same day of the week as the date when the current VLF data VDA is acquired. For example, the current VLF data VDA and the past VLF data VDB on every Monday of each week can be compared. In addition, the current VLF data VDA and the past VLF data VDB on the first day of each month can also be compared. The time interval of the acquired past VLF data VDB is arbitrary.

[0194] Next, the state estimation unit 17 combines the plurality of past VLF data VDB and the current VLF data VDA to create trend data TD (S53). The trend data TD is data that summarizes the VLF data VD from the past to the current into one, and can judge the trend of the VLF data VD from the past to the current.

[0195] Next, the state estimation unit 17 determines whether the trend data TD of the nearest past when the current VLF data VDA is acquired is in a decreasing trend for the trend data TD (S54).

[0196] As the trend data TD, for example, a state in which a plurality of past VLF data VDB monotonically decreases to the current VLF data VDA can be cited. In this case, the trend data TD of the most recent past when the current VLF data VDA is obtained is in a decreasing trend. Therefore, the state estimation unit 17 determines that the trend data TD of the most recent past when the current VLF data VDA is obtained is in a decreasing trend (S54: Yes).

[0197] In addition, as the trend data TD, for example, a state in which a plurality of past VLF data VDB repeatedly decreases and increases periodically up to the current VLF data VDA can be cited. In this case, the trend data TD of the most recent past when the current VLF data VDA is obtained is either in a decreasing trend or in an increasing trend. When the trend data TD of the most recent past when the current VLF data VDA is obtained is in a decreasing trend, the state estimation unit 17 determines that the trend data TD is in a decreasing trend (S54: Yes).

[0198] When the trend data TD is in a decreasing trend (S54: Yes), as a whole, it can be determined that the VLF data VD related to the health state of the mobile body user is in a decreasing trend. Therefore, the state estimation unit 17 determines that the health state of the mobile body user has changed in a bad direction (S55). Thus, the state estimation process 5 (S50) ends.

[0199] On the other hand, when the trend data TD is not in a decreasing trend (S54: No), the state estimation process 5 (S50) ends.

[0200] It should be noted that as the trend of the above-mentioned VLF data VD, it includes both or either of a state in which a plurality of past VLF data VDB monotonically decreases to the current VLF data VDA and a state in which a plurality of past VLF data VDB repeatedly decreases and increases periodically up to the current VLF data VDA.

[0201] 3.3. Service provision process S5

[0202] When the health state of the mobile body user changes in a bad direction, the user interface 18 provides a specific service to the mobile body user.

[0203] As the specific service, there is no particular limitation. For example, the following services can be provided. The service provision unit can, for example, convey a message clearly indicating that the health state has changed in a bad direction to the mobile body user by voice or display it on the screen. The message is not particularly limited. For example, "You seem to be a bit tired recently.", "It is recommended that you take a rest.", etc. can be adopted as any message.

[0204] In addition, the user interface 18 can also convey to the mobile body user a message suggesting a direction towards an improved health state by voice or display it on the screen. The message is not particularly limited, and for example, any message such as "It is recommended that you do some exercise" or "It is recommended that you travel" can be adopted.

[0205] In addition, the user interface 18 can also convey to the mobile body user the facilities that can be expected to restore the health state and the distance to the facilities. The service providing unit can also provide the mobile body user with information such as the summary, business hours, distance, and cost of the facilities according to the preferences of the mobile body user, for example, for sports facilities, hot springs, leisure areas, tourist attractions, art galleries, etc.

[0206] According to this method, based on the VLF data VD obtained from the mobile body user on board the mobile body 11, the current VLF data VDA at the current boarding and the past VLF data VDB at the past boarding are relatively compared, and thus the change in the health state of the mobile body user can be estimated. Based on the change in the health state thus estimated, services related to the health state can be provided to the mobile body user.

[0207] (Embodiment 1.2)

[0208] Next, refer to Figures 11 - 13 Embodiment 1.2 will be described. It should be noted that among the reference numerals used in Embodiment 1.2 and later, the same reference numerals as those used in the already presented embodiments represent the same constituent elements and the like as those in the already presented embodiments, unless otherwise specifically shown.

[0209] As Figure 11 shown, the difference between the health information service providing apparatus 10 of this method and Embodiment 1.1 is that the storage unit 60 stores a specific threshold TVD, and the threshold TVA includes a normal threshold TVE and a warning threshold TVF. The warning threshold TVF is a value smaller than the normal threshold TVE.

[0210] In addition, the difference between this method and Embodiment 1.1 is that instead of the state estimation process 1 (S10), the state estimation process 6 (S60) is executed (refer to Figure 12 ).

[0211] Figure 12 The flowchart showing the state estimation process 6 (S60). The state estimation process 6 (S60) of this method will be described in detail later. It is a method that uses the normal threshold TVE when the current VLF data VDA is greater than the specific threshold TVD and uses the warning threshold TVF when the current VLF data VDA is less than or equal to the specific threshold TVD. When the state estimation process 6 (S60) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11).

[0212] Next, the state estimation unit 17 executes the pre-judgment process 1 (S61). Figure 13 The flowchart of the subroutine representing the pre-judgment process 1 (S61).

[0213] When executing the pre-judgment process 1 (S61), the state estimation unit 17 determines whether the current VLF data VDA is greater than the specific threshold value TVD stored in the storage unit 60 (S62). That is, in this method, a process focusing on the value of the current VLF data VDA itself is included.

[0214] When the current VLF data VDA is greater than the specific threshold value TVD (S62: Yes), the state estimation unit 17 uses the normal threshold value TVE as the threshold value TVA (S63). Thereby, the pre-judgment process 1 (S61) ends and returns to the state estimation process 6 (S60).

[0215] On the other hand, when the current VLF data VDA is equal to or less than the specific threshold value TVD (S62: No), the state estimation unit 17 uses the warning threshold value TVF as the threshold value TVA (S64). Thereby, the pre-judgment process 1 (S61) ends and returns to the state estimation process 6 (S60).

[0216] The processes (S12 to S18) after returning to the state estimation process 6 (S60) are the same as the state estimation process 1 (S10) of the first embodiment 1.1, so the repeated description is omitted.

[0217] Next, the effects of this method will be described. As described above, the warning threshold value TVF is a value smaller than the normal threshold value TVE. Therefore, when using the warning threshold value TVF as the threshold value TVA, it is easy to judge that the health state of the mobile body user has changed in a bad direction.

[0218] The current VLF data VDA is information related to the current health state of the mobile body user. As described above, when the value of the current VLF data VDA is large, it is presumed that the health state of the mobile body user is good, and when the value of the current VLF data VDA is small, it is presumed that the health state of the mobile body user is bad. When the current VLF data VDA is large enough to be greater than the specific threshold value TVD, it is presumed that the health state of the mobile body user is in a good trend, so the normal threshold value TVE is used as the threshold value TVA.

[0219] On the other hand, when the VDA of the current VLF data is below a specific threshold value TVD, it is presumed that the health state of the mobile body user was originally in a poor state. Therefore, by using a value smaller than the normal threshold value TVE, that is, the warning threshold value TVF, as the threshold value TVA, when it is presumed that the health state of the mobile body user is in a poor state, it is easier to presume that the health state of the mobile body user is poor. Thus, it is possible to suppress the situation where the mobile body user reluctantly engages in activities despite being in a poor health state.

[0220] (Embodiment 1.3)

[0221] Next, with reference to Figures 14 - 15 , Embodiment 1.3 will be described. As Figure 14 shown, the difference between the health information service providing apparatus 10 of this embodiment and that of Embodiment 1.1 is that the storage unit 60 stores the first threshold value TVG and the second threshold value TVH.

[0222] In addition, the difference between this embodiment and Embodiment 1.1 is that instead of the state estimation process 1 (S10), the state estimation process 7 (S70) is executed (refer to Figure 15 ).

[0223] Figure 15 FIG. shows a flowchart of the state estimation process 7 (S70). The state estimation process 7 (S70) of this embodiment will be described in detail later. It is as follows: when the first difference value ΔDVF obtained by subtracting the current VLF data VDA from the VLF data VDC of the first past period is equal to or greater than the first threshold value TVG, and the second difference value ΔDVG obtained by subtracting the current VLF data VDA from the VLF data VDD of the second past period is equal to or greater than the second threshold value TVH, it is presumed that the health state of the mobile body user has changed in a bad direction. When the state estimation process 7 (S70) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S71) as the VLF data VD at the current boarding or the most recent boarding.

[0224] Next, the past VLF data acquisition unit 16 acquires the VLF data VDC of the first past period (S72), and the VLF data VDC of the first past period is the statistical representative value of the VLF data VD within the first period before the current boarding or the most recent boarding.

[0225] Next, the past VLF data acquisition unit 16 acquires the VLF data VDD of the second past period (S73), and the VLF data VDD of the second past period is the statistical representative value of the VLF data VD within the second period longer than the first period of the VLF data VDC of the first past period.

[0226] Next, the state estimation unit 17 calculates a first difference value ΔDVF obtained by subtracting the current VLF data VDA from the first past period VLF data VDC (S74).

[0227] Next, the state estimation unit 17 calculates a second difference value ΔDVG obtained by subtracting the current VLF data VDA from the second past period VLF data VDD (S75).

[0228] Next, the state estimation unit 17 determines whether the first difference value ΔDVF is equal to or greater than a first threshold value TVG (S76), and further determines whether the second difference value ΔDVG is equal to or greater than a second threshold value TVH (S77).

[0229] When the first difference value ΔDVF is equal to or greater than the first threshold value TVG (S76: Yes) and the second difference value ΔDVG is equal to or greater than the second threshold value TVH (S77: Yes), the state estimation unit 17 presumes that the health state of the mobile body user has changed in a bad direction (S78). Thus, the state estimation process 7 (S70) ends.

[0230] On the other hand, when the first difference value ΔDVF is less than the first threshold value TVG (S76: No) and the second difference value ΔDVG is less than the second threshold value TVH (S77: No), the state estimation unit 17 ends the state estimation process 7 (S70).

[0231] According to this method, as comparison objects with the current VLF data VDA, the first past period VLF data VDC within the first period and the second past period VLF data VDD within the second period longer than the first period are used. By making comparisons in different periods in this way, the health state of the mobile body user can be presumed in more aspects. However, the combination of the first period and the second period is not particularly limited. For example, any combination such as the combination of the last ride and the ride the day before, the combination of the last ride and the most recent week, the combination of the ride the day before and the most recent week, etc. can be appropriately selected.

[0232] (Embodiment 1.4)

[0233] Next, refer to Figure 16 to describe Embodiment 1.4. The difference between this method and Embodiment 1.3 is that the state estimation process (S80) is executed instead of the state estimation process 7 (S70) (refer to Figure 16 ).

[0234] As Figure 16 shown, the state estimation process 8 is the same as the state estimation process 7 (S70) described in Figure 15 before S71 to S74, and the processes after S75 are different. For the same processes as the state estimation process 7 (S70), repeated descriptions are omitted.

[0235] In the state estimation process 8 (S80) of this method, when the first difference value ΔDVF obtained by subtracting the current VLF data VDA from the first past period VLF data VDC is equal to or greater than the first threshold value TVG, it is presumed that the health state of the mobile body user has changed in an unfavorable direction. Further, when the first difference value ΔDVF is smaller than the first threshold value TVG and the second difference value ΔDVG obtained by subtracting the current VLF data VDA from the second past period VLF data VDD is equal to or greater than the second threshold value TVH, it is presumed that the health state of the mobile body user has changed in an unfavorable direction.

[0236] As Figure 16 shown, after calculating the first difference value ΔDVF (S74), the state estimation unit 17 determines whether the first difference value ΔDVF is equal to or greater than the first threshold value TVG (S76).

[0237] When the first difference value ΔDVF is equal to or greater than the first threshold value TVG (S76: Yes), the state estimation unit 17 presumes that the health state of the mobile body user has changed in an unfavorable direction (S78). Thereby, the state estimation process 8 (S80) ends.

[0238] On the other hand, when the first difference value ΔDVF is smaller than the first threshold value TVG (S76: No), the state estimation unit 17 calculates the second difference value ΔDVG (S75).

[0239] Next, the state estimation unit 17 determines whether the second difference value ΔDVG is equal to or greater than the second threshold value TVH (S77).

[0240] When the second difference value ΔDVG is equal to or greater than the second threshold value TVH (S77: Yes), the state estimation unit 17 presumes that the health state of the mobile body user has changed in an unfavorable direction (S78). Thereby, the state estimation process 8 (S80) ends.

[0241] On the other hand, when the second difference value ΔDVG is smaller than the second threshold value TVH (S77: No), the state estimation process 8 (S80) ends.

[0242] According to this method, as comparison objects with the current VLF data VDA, the first past period VLF data VDC within the first period and the second past period VLF data VDD within the second period longer than the first period are used. Thereby, by making comparisons in different periods, it is possible to more comprehensively estimate the health state of the mobile body user.

[0243] (Embodiment 1.5)

[0244] Next, referring to Figures 17 - 18A description will be given of Embodiment 1.5. As Figure 17 shown, in the health information service providing apparatus 10 of this embodiment, the difference from Embodiment 1.1 is that the cloud 59 is provided with a minimum VLF data acquisition unit 61. The minimum VLF data VDE is the minimum value of the VLF data VD over a period longer than the past specific period in the past VLF data VDB.

[0245] In addition, the difference between this embodiment and Embodiment 1.1 is that instead of the state estimation process 1 (S10), a state estimation process 9 (S90) is executed (refer to Figure 18 ).

[0246] Figure 18 FIG. shows a flowchart of the state estimation process 9 (S90). The state estimation process 9 (S90) of this embodiment will be described in detail later. It is a method of comparing the current VLF data VDA with the past VLF data VDB and then comparing the current VLF data VDA with the lowest VLF data VD measured in the past, that is, the minimum VLF data VDE. The difference between the state estimation process 9 (S90) and Figure 6 the state estimation process 1 (S10) of is that a process (S91) of the minimum VLF data acquisition unit 61 acquiring the minimum VLF data VDE and a process (S92) of the state estimation unit 17 determining whether the current VLF data VDA is less than the minimum VLF data VDE are executed. Therefore, in the following description, the same reference numerals are given to the same processes as those in the state estimation process 1 (S10), and the repeated description is omitted.

[0247] As Figure 18 shown, in the state estimation process 9 (S90), when the second past difference value ΔDVB is less than the threshold value TVA (S18: No), the minimum VLF data acquisition unit 61 acquires the minimum VLF data VDE from the storage unit 60 (S91).

[0248] Next, the state estimation unit 17 determines whether the current VLF data VDA is less than the minimum VLF data VDE (S92). That is, in this embodiment, the value of the current VLF data VDA is compared with the lowest value of the VLF data VD acquired in the past.

[0249] When the current VLF data VDA is less than the minimum VLF data VDE (S92: Yes), the state estimation unit 17 presumes that the health state of the mobile body user has changed in a bad direction (S16). Thus, the state estimation process 9 (S90) ends.

[0250] On the other hand, when the current VLF data VDA is equal to or greater than the minimum VLF data VDE (S92: No), the state estimation process 9 (S90) ends.

[0251] If only the current VLF data VDA is relatively compared with the first past VLF data VDF and the second past VLF data VDG, when the first past difference value ΔDVA is equal to or greater than the threshold value TVA and the second past difference value ΔDVB is equal to or greater than the threshold value TVA, the state estimation unit 17 does not determine that the health state of the mobile body user has changed in a bad direction. However, according to this method, even when the first past difference value ΔDVA is equal to or greater than the threshold value TVA and the second past difference value ΔDVB is equal to or greater than the threshold value TVA, if the current VLF data VDA is less than the minimum VLF data VDE, the state estimation unit 17 also estimates that the health state of the mobile body user has changed in a bad direction. Thus, the health state of the mobile body user can be estimated more accurately.

[0252] (Embodiment 1.6)

[0253] Next, with reference to Figure 19 , Embodiment 1.6 will be described. The difference between this method and Embodiment 1.5 is that state estimation process 10 (S100) is executed instead of state estimation process 9 (S90).

[0254] Figure 19 The flowchart showing state estimation process 10 (S100). As will be described in detail later, it is a method of comparing the current VLF data VDA and the lowest VLF data VD measured in the past, that is, the minimum VLF data VDE, before comparing the current VLF data VDA and the past VLF data VDB. The difference between state estimation process 10 (S100) and Figure 18 the state estimation process 9 (S90) of

[0255] is that the process (S91) of the minimum VLF data acquisition unit 61 for acquiring the minimum VLF data VDE and the process (S92) of the state estimation unit 17 for determining whether the current VLF data VDA is less than the minimum VLF data VDE are executed after the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11). Figure 19 As shown in

[0256] After the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11), the minimum VLF data acquisition unit 61 acquires the minimum VLF data VDE from the storage unit 60 (S91).

[0257] When the current VLF data VDA is less than the lowest VLF data VDE in this case (S92: Yes), the state estimation unit 17 estimates that the health state of the mobile body user has changed in a bad direction (S16). Thereby, the state estimation process 10 (S100) ends.

[0258] On the other hand, when the current VLF data VDA is equal to or greater than the lowest VLF data VDE in this case (S92: No), the processes after S12 are executed. The processes of S12 to S18 are the same as those of Figure 6 the state estimation process 1 (S10), so the repeated description is omitted.

[0259] According to this method, when the current VLF data VDA is less than the lowest VLF data VDE, the state estimation unit 17 immediately estimates that the health state of the mobile body user has changed in a bad direction. Thereby, it is possible to quickly estimate that the health state of the mobile body user has changed in a bad direction.

[0260] (Embodiment 1.7)

[0261] Next, with reference to Figures 20 - 21 , Embodiment 1.7 will be described. As Figure 20 shown, the difference between this method and Embodiment 1.1 is that the storage unit 60 stores the emergency threshold TVI.

[0262] In addition, the difference from Embodiment 1.1 is that the state estimation process 11 (S110) is executed instead of the state estimation process 1 (S10).

[0263] Figure 21 The flowchart showing the state estimation process 11 (S110). The state estimation process 11 (S110) of this method will be described in detail later. It is a method of comparing the current VLF data VDA and the emergency threshold TVI before comparing the current VLF data VDA and the past VLF data VDB. When the state estimation process 11 (S110) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11).

[0264] Next, the state estimation unit 17 determines whether the current VLF data VDA is less than or equal to the emergency threshold TVI (S111). When the current VLF data VDA is less than or equal to the emergency threshold TVI (S111: Yes), the state estimation unit 17 estimates that the health state of the mobile body user has changed in a bad direction (S16). Thereby, the state estimation process 11 (S110) ends.

[0265] On the other hand, when the VDA of the current VLF data is greater than the emergency threshold TVI (S111: No), the processes of S12 to S18 are executed. The processes of S12 to S18 are the same as the state estimation process 1 (S10) of Embodiment 1.1, so redundant explanations are omitted.

[0266] According to this mode, when the VDA of the current VLF data is below the emergency threshold TVI, the state estimation unit 17 immediately estimates that the health state of the mobile body user has changed in a bad direction. Thereby, it is possible to quickly estimate that the health state of the mobile body user has changed in a bad direction.

[0267] However, it is also possible to adopt a mode in which after comparing the current VLF data VDA with the past VLF data VDB, the current VLF data VDA is compared with the emergency threshold TVI.

[0268] (Embodiment 1.8)

[0269] Next, refer to Figures 22 - 23 , and an explanation of Embodiment 1.8 will be given. As Figure 22 shown, the difference between the storage unit 60 involved in this mode and that of Embodiment 1.1 is that instead of the threshold TVA, it has a first past threshold TVJ (an example of a first comparison reference) and a second past threshold TVK (an example of a second comparison reference). This mode uses the first past threshold TVJ and the second past threshold TVK to estimate the health state of the mobile body user.

[0270] In addition, the difference between this mode and Embodiment 1.1 is that instead of the state estimation process 1 (S10), the state estimation process 12 (S120) is executed (refer to Figure ).

[0271] As ​ shown, compared with ​ , the difference between the state estimation process 12 (S120) and the state estimation process 1 (S10) is that S121 is executed instead of S15, and S122 is executed instead of S18. The same reference numerals are used for the same processes as those in the state estimation process 1 (S10), and redundant explanations are omitted.

[0272] The state estimation process 12 (S120) of this mode will be described in detail later. It is a mode in which the first past threshold TVJ is used to judge the first past difference value ΔDVA, and the second past threshold TVK is used to judge the second past difference value ΔDVB.

[0273] After calculating the first past difference value ΔDVA (S14), the state estimation unit 17 determines whether the first past difference value ΔDVA is equal to or greater than the first past threshold value TVJ (S121).

[0274] When the first past difference value ΔDVA is equal to or greater than the first past threshold value TVJ (S121: Yes), the state estimation unit 17 estimates that the health state of the mobile body user has changed in an adverse direction (S16). Thereby, the state estimation process 12 (S120) ends.

[0275] On the other hand, when the first past difference value ΔDVA is less than the first past threshold value TVJ (S121: No), the state estimation unit 17 calculates a second past difference value ΔDVB (S17). Next, the state estimation unit 17 determines whether the second past difference value ΔDVB is equal to or greater than the second past threshold value TVK (S122).

[0276] When the second past difference value ΔDVB is equal to or greater than the second past threshold value TVK (S122: Yes), the state estimation unit 17 estimates that the health state of the mobile body user has changed in an adverse direction (S16). Thereby, the state estimation process 12 (S120) ends.

[0277] On the other hand, when the second past difference value ΔDVB is less than the second past threshold value TVK (S122: No), the state estimation process 12 (S120) ends.

[0278] According to this mode, the first past threshold value TVJ is used to judge the first past difference value ΔDVA, and the second past threshold value TVK is used to judge the second past difference value ΔDVB. Thereby, the health state of the mobile body user can be accurately judged.

[0279] (Embodiment 1.9)

[0280] Next, with reference to ​ , Embodiment 1.9 will be described. As ​ shown, the difference between the storage unit 60 of this mode and Embodiment 1.8 is that: a specific threshold value TVD is stored; the first past threshold value TVJ includes a first past normal threshold value TVL and a first past warning threshold value TVM; and the second past threshold value TVK includes a second past normal threshold value TVN and a second past warning threshold value TVO. The first past warning threshold value TVM is a value smaller than the first past normal threshold value TVL. The second past warning threshold value TVO is a value smaller than the second past normal threshold value TVN.

[0281] In addition, the difference between this mode and Embodiment 1.8 is that, instead of the state estimation process 12 (S120), the state estimation process 13 (S130) is executed ( ​ ).

[0282] The state estimation process 13 (S130) of this method, which will be described in detail later, is as follows: when the current VLF data VDA is greater than a specific threshold value TVD, the first past normal threshold value TVL and the second past normal threshold value TVN are used to estimate the health state of the mobile body user; when the current VLF data VDA is less than or equal to the specific threshold value TVD, the first past warning threshold value TVM and the second past warning threshold value TVO are used to estimate the health state of the mobile body user.

[0283] As ​ shown, the difference between the state estimation process 13 (S130) and ​ the state estimation process 12 (S120) is that after executing S11, a pre-judgment process 2 (S131) is executed. The same reference numerals are used for the same processes as those in the state estimation process 12 (S120), and repeated descriptions are omitted.

[0284] As ​ shown, when the state estimation process 13 (S130) is executed, the current VLF data acquisition unit 15 acquires the current VLF data VDA (S11). Then, the state estimation unit 17 executes the pre-judgment process 2 (S131).

[0285] ​ The flowchart of the subroutine representing the pre-judgment process 2 (S131). When the pre-judgment process 2 (S131) is executed, the state estimation unit 17 determines whether the current VLF data VDA is greater than the specific threshold value TVD stored in the storage unit 60 (S132).

[0286] When the current VLF data VDA is greater than the specific threshold value TVD (S132: Yes), the state estimation unit 17 uses the first past normal threshold value TVL as the first past threshold value TVJ (S133), and uses the second past normal threshold value TVN as the second past threshold value TVK (S134). Thus, the pre-judgment process 2 (S131) ends.

[0287] On the other hand, when the current VLF data VDA is less than or equal to the specific threshold value TVD (S132: No), the state estimation unit 17 uses the first past warning threshold value TVM as the first past threshold value TVJ (S135), and uses the second past warning threshold value TVO as the second past threshold value TVK (S136). Thus, the pre-judgment process 2 (S131) ends.

[0288] Return to ​ , the processes of S12 to S14, S121, S16, S17, and S122 are the same as those in ​is the same as the state estimation process 12 (S120), so the same reference numerals are used and repeated descriptions are omitted.

[0289] Next, the effects of this method will be described. As described above, the first past warning threshold TVM is a value smaller than the first past normal threshold TVL, and the second past warning threshold TVO is a value smaller than the second past normal threshold TVN. Therefore, if the first past warning threshold TVM is used as the first past threshold TVJ and the second past warning threshold TVO is used as the second past threshold TVK, it is easy to determine that the health state of the mobile body user has changed in a bad direction.

[0290] In addition, when the current VLF data VDA is equal to or less than a specific threshold value TVD, it is presumed that the health state of the mobile body user is originally in a bad state. Therefore, when the current VLF data VDA is equal to or less than the specific threshold value TVD, as the threshold value TVA, the first past warning threshold TVM is used as the first past threshold TVJ, and the second past warning threshold TVO is used as the second past threshold TVK. Thus, when it is presumed that the health state of the mobile body user is in a bad state, it is easier to presume that the health state of the mobile body user is bad. Thereby, it is possible to suppress the situation where the mobile body user reluctantly performs activities despite being in a bad health state.

[0291] The present disclosure is not limited to the above-described embodiments, and can be applied to the following methods within the scope not departing from the gist thereof.

[0292] (1.1) In Embodiment 1.1, the sensor 12 is configured to be mounted on the seat 21, and the biological signal BS is acquired according to the change in the body movement of the mobile user sitting on the seat 21. However, it is not limited thereto. The sensor may also emit light (infrared rays, ultraviolet rays, laser, visible light, etc.), sound, etc. to the mobile user, and detect the reflection from the mobile user. In addition, it may be a Doppler sensor that emits microwaves to the mobile body user and detects the change in the body movement of the mobile body user based on the difference between the transmitted frequency and the received frequency. Any sensor can be intentionally selected.

[0293] (1.2) In Embodiment 1.1, the sensor 12 is configured to be installed inside the seat surface portion 22a. However, it is not limited thereto. As ​ shown, the sensor 12 may also be configured to place a component separate from the seat 21 on the upper surface of the seat surface portion 22a (the upper surface of the seat surface skin member 33), and install it on the seat surface portion 22a by known mounting means such as rubber bands and belts. In addition, the sensor 12 may be configured to be installed on the seat back portion 22b by known mounting means such as rubber bands and belts.

[0294] (1.3) In Embodiment 1.1, the user interface 18 is an in-vehicle navigation system assembled in the mobile body 11, but it is not limited thereto. As shown in ​ , it may also be a smartphone, a tablet terminal, a smartwatch, etc. that are separate from the mobile body 11. It should be noted that, in ​ , the data stored in the storage unit 60 is omitted. According to this embodiment, the user interface 18 can provide specific services to the mobile body user who is not on board the mobile body 11. For example, it is also possible to transmit a message regarding the health status of the mobile body user to the mobile body user who has gotten off the mobile body 11 and is relaxing at home through an image or sound, or display guidance or a route of a sports facility, etc.

[0295] (1.4) In Embodiment 1.1, the user interface 18 transmits or receives information to / from the cloud 59 via the network 58, but it is not limited thereto. As shown in ​ , the configuration of the cloud 59 in Embodiment 1.1 may also be configured as a configuration assembled in the mobile body 11 as the control device 62.

[0296] (1.5) In Embodiment 1.1, the user interface 18 transmits or receives information to / from the cloud 59 via the network 58, but it is not limited thereto. As shown in ​ , it may also be configured such that the ECU 57 transmits the VLF data VD to the cloud 59 via the network 58, and the user interface 18 (for example, an in-vehicle navigation system) assembled in the mobile body 11 provides information to the mobile body user.

[0297] (1.6) In Embodiment 1.1, the user interface 18 transmits or receives information to / from the cloud 59 via the network 58, but it is not limited thereto. As shown in ​ , it may also be configured such that the ECU 57 transmits the VLF data VD to the cloud 59 via the network 58, and the user interface 18 (for example, a smartphone, a tablet terminal, a smartwatch) that is separate from the mobile body 11 provides information to the mobile body user.

[0298] (1.7) The ECU 57 of Embodiment 1.1 is configured to include the calculation unit 14, but it is not limited thereto. As shown in ​ , it may also be configured such that the cloud 59 includes the calculation unit 14. At this time, it may also be configured such that the ECU 57 transmits the heartbeat signal HS to the cloud 59 via the network 58, and the user interface 18 (for example, a smartphone, a tablet terminal, a smartwatch) that is separate from the mobile body 11 provides information to the mobile body user.

[0299] (1.8) The ECU 57 of Embodiment 1.1 is configured to include the calculation unit 14, but it is not limited thereto. As shown in ​As shown, it may also be configured such that the cloud 59 has a calculation unit 14. In this case, it may also be configured such that the ECU 57 sends a heartbeat signal HS to the cloud 59 via the network 58, and the user interface 18 (e.g., a car navigation system) assembled in the mobile body 11 provides information to the user of the mobile body.

[0300] (1.9) The mobile body 11 of Embodiment 1.1 is configured to include an estimation unit 13 and a calculation unit 14, but is not limited thereto. As ​ shown, it may also be configured such that the cloud 59 has an estimation unit 13 and a calculation unit 14.

[0301] (1.10) The mobile body 11 of Embodiment 1.1 is configured to include an estimation unit 13 and a calculation unit 14, but is not limited thereto. As ​ shown, it may also be configured such that the cloud 59 has an estimation unit 13 and a calculation unit 14, and the user interface 18 (e.g., a smart phone, a tablet terminal, a smart watch) separated from the mobile body 11 sends or receives information to / from the cloud 59 via the network 58.

[0302] (Embodiment 2.1)

[0303] 1. Outline of the drowsiness information service providing device 101

[0304] Refer to ​ to explain the outline of the drowsiness information service providing device 101 (an example of a health information service providing device) according to Embodiment 2.1. The drowsiness information service providing device 101 of this embodiment provides a service related to drowsiness information regarding the drowsiness of a passenger riding in the mobile body 102. Among them, the health information includes drowsiness information.

[0305] The mobile body 102 in this embodiment refers to a means of transportation such as a passenger vehicle, a freight vehicle, a work vehicle, etc., a tram, a ship, an airplane, a helicopter, a passenger drone, etc. that a person rides on.

[0306] As ​ shown, the drowsiness information service providing device 101 of this embodiment includes a sensor 110, a control circuit 111, an estimation unit 112, a calculation unit 113, a current drowsiness omen data acquisition unit 114, a past drowsiness omen data acquisition unit 115, a state estimation unit 116, a service providing unit 117, a user interface 118 (an example of a providing device), and a mobile body safety device 119 (an example of a providing device).

[0307] The moving body 102 is provided with a seat 21 for a passenger to sit on. A sensor 110 is installed on the seat 21. When the seat 21 is applied to the driver's seat, the seat 21 is used to detect the sitting state of the driver during driving and the biological signal BS of the driver. When the seat 21 is applied to a seat different from the driver's seat, the seat 21 is used to detect the sitting state of the passenger of the moving body 102 different from the driver and the biological signal BS.

[0308] As ​ shown, the seat 21 includes a frame portion 28, a cushion portion 29, and a sensor 110. The seat 21 of this embodiment includes a headrest 22c. However, the headrest 22c may be omitted.

[0309] The frame portion 28 includes a seat surface seat frame 31 and a back seat frame 41. The cushion portion 29 includes a seat surface seat cushion 30 installed on the seat surface seat frame 31 and a back seat cushion 42 installed on the back seat frame 41. The seat surface seat cushion 30 includes a first seat surface seat cushion 32 and a second seat surface seat cushion 35.

[0310] The seat surface seat frame 31 is formed of a hard material such as metal or hard resin, and is installed on the moving body 102. The seat surface seat frame 31 has a plate-like portion. The plate-like portion is installed on the moving body 102 with the plate surface facing the up-and-down direction. The upper surface of the plate-like portion is formed as a mounting seat surface 31a for mounting the first seat surface seat cushion 32. The portion of the seat surface seat frame 31 different from the plate-like portion is formed into an arbitrary shape such as a rod shape or a column shape.

[0311] The first seat surface seat cushion 32 is formed of an elastic material such as foamed resin. The first seat surface seat cushion 32 is installed in a state of being placed on the mounting seat surface 31a formed on the upper surface of the seat surface seat frame 31. The upper surface of the first seat surface seat cushion 32 is formed as a pressure-receiving surface 32a that receives pressure from the passenger's buttocks. The lower surface of the first seat surface seat cushion 32, that is, the surface on the back side of the pressure-receiving surface 32a, i.e., the anti-pressure-receiving surface 32b, faces the mounting seat surface 31a of the seat surface seat frame 31.

[0312] The first seat surface seat cushion 32 has a storage recess 50 that opens downward to the side of the seat surface seat frame 31 on the anti-pressure-receiving surface 32b. The cross-sectional shape of the storage recess 50 can be set to an arbitrary shape such as a polygon, a circle, or an oval. The cross-sectional shape of the storage recess 50 in this embodiment is a quadrilateral. The portion of the storage recess 50 located on the side opposite to the direction in which the storage recess 50 opens is formed as the bottom 52 of the storage recess 50.

[0313] The second seat surface cushion 35 is received in the receiving recess 50. The second seat surface cushion 35 is mounted on the mounting seat surface 31a of the seat surface seat frame 31. The surface of the second seat surface cushion 35 that faces the mounting seat surface 31a of the seat surface seat frame 31 is formed as the mounting surface 35b. In a state where the first seat surface cushion 32 and the second seat surface cushion 35 are mounted on the seat surface seat frame 31, the non-pressure-receiving surface 32b of the first seat surface cushion 32 and the mounting surface 35b of the second seat surface cushion 35 are coplanar. In addition, in a state where the first seat surface cushion 32 and the second seat surface cushion 35 are mounted on the seat surface seat frame 31, a gap is formed between the inner side surface of the receiving recess 50 and the outer side surface of the second seat surface cushion 35. The upper surface of the second seat surface cushion 35 (the surface on the side opposite to the seat surface seat frame 31) is formed as the second pressing surface 35a that presses the sensor 110 from below. However, it may also be configured such that the receiving recess 50 of the first seat surface cushion 32 opens upward, and the second seat surface cushion 35 is received in the receiving recess 50.

[0314] A seat surface skin member 33 is laminated on the surface of the first seat surface cushion 32. The seat surface skin member 33 covers at least the pressure-receiving surface 32a of the first seat surface cushion 32. The seat surface skin member 33 is formed of a material such as cloth or leather that is less stretchable than the first seat surface cushion 32.

[0315] The back seat frame 41 is formed of a hard material such as metal or hard resin, for example. The back seat frame 41 is formed in a plate shape, a rod shape, or the like. For example, when the seat body 22 is provided with a backrest adjustment function, the back seat frame 41 is swingably supported by the seat surface seat frame 31. Of course, the back seat frame 41 may also be integrally fixed to the seat surface seat frame 31.

[0316] The back seat cushion 42 is formed of an elastic material such as foamed resin. The back seat cushion 42 is laminated and mounted on the back seat frame 41. The surface of the back seat cushion 42 on the side opposite to the back seat frame 41 is formed as the pressure-receiving surface 42a that is pressured by the back of the occupant. In addition, the surface of the back seat cushion 42 that faces the back seat frame 41 is formed as the non-pressure-receiving surface 42b of the back seat cushion 42.

[0317] A back skin member 43 is covered on the surface of the back seat cushion 42. The back skin member 43 covers at least the pressure-receiving surface 42a of the back seat cushion 42. The back skin member 43 is formed of materials such as cloth or leather.

[0318] The headrest 22c is disposed at the upper end of the seat back portion 22b. The headrest 22c includes a cushion 45 and a skin member 46. Here, in ​In this case, the first seat surface seat cushion 32 and the back seat cushion 42 are separate, but they can also be integrated. Additionally, the back seat cushion 42 and the headrest 22c are separate, but they can also be integrated.

[0319] The sensor 110 is disposed between a first pressing surface 52b formed in a receiving recess 50 of the first seat surface seat cushion 32 and a second pressing surface 35a of the second seat surface seat cushion 35. The first pressing surface 52b is provided on a convex portion 52a protruding downward. Here, when a passenger sits on the seat body 22, pressure is applied from the passenger's buttocks to the pressure receiving surface 32a of the first seat surface seat cushion 32, and this pressure is transmitted through the first seat surface seat cushion 32 to the first pressing surface 52b of the first seat surface seat cushion 32. Moreover, the sensor 110 receives pressure from the first pressing surface 52b of the first seat surface seat cushion 32. That is, in the seated state of the passenger, the sensor 110 detects a physical quantity corresponding to the pressure transmitted through the first seat surface seat cushion 32 from the pressure receiving surface 32a of the first seat surface seat cushion 32.

[0320] Here, the sensor 110 is disposed on the seat seat surface portion 22a, but it can also be disposed on the seat back surface portion 22b. In this case, the sensor 110 is disposed between the back seat frame 41 and the back seat cushion 42. Moreover, in the seated state of the passenger, the sensor 110 detects a physical quantity corresponding to the pressure transmitted through the back seat cushion 42 from the pressure receiving surface 32a of the back seat cushion 42.

[0321] Return to ​ The sensor 110 is connected to a control circuit 111 for controlling the sensor 110. The control circuit 111 controls the operation of the sensor 110 and acquires the physical quantity detected by the sensor 110 from the sensor 110. The control circuit 111 detects the biological signal BS of the passenger for the physical quantity acquired from the sensor 110. The control circuit 111 can also perform processing such as amplification and noise elimination on the biological signal BS.

[0322] The sensor 110 and the control circuit 111 constitute a monitoring system 156 (an example of an acquisition device) for monitoring the biological signal BS of the passenger.

[0323] The control circuit 111 sends the biological signal BS to the ECU 157 (Electrical Control Unit). The ECU 157 includes a presumption unit 112 and a calculation unit 113.

[0324] The estimation unit 112 acquires a biological signal BS obtained from the control circuit 111 of the monitoring system 156. The biological signal BS is a superordinate concept of the passenger's heartbeat, pulse, body movement, respiration, etc. In addition, it also includes the case where signals such as heartbeat, pulse, body movement, and respiration are mixed. Pulse refers to the pulsation generated in the artery. On the other hand, heartbeat refers to the pulsation of the heart pumping blood throughout the body. In the case of a healthy person, the heartbeat and pulse usually coincide. Therefore, hereinafter, the heartbeat and pulse will be collectively referred to as the heartbeat signal HS related to the heartbeat. The estimation unit 112 estimates the heartbeat signal HS related to the passenger's heartbeat based on the biological signal BS.

[0325] The calculation unit 113 calculates drowsiness omen data DD related to the passenger's drowsiness omen based on the heartbeat signal HS. The drowsiness omen data DD is the detection frequency or the related value of the detection frequency of the drowsiness omen per unit time measured within a predetermined measurement time. In this mode, it is determined whether the passenger is drowsy based on the change in the time interval of the passenger's heartbeat calculated based on the heartbeat signal HS. It should be noted that in the following description, the time interval of the passenger's heartbeat will be simply referred to as the heartbeat interval.

[0326] Refer to ​ , and the drowsiness omen data DD will be described. ​ The curve shown in the curve graph shows the change in the heartbeat interval over time. An increase in the heartbeat interval means that the passenger's heartbeat beats slowly. A decrease in the heartbeat interval means that the passenger's heartbeat beats rapidly.

[0327] ​ The waveform of the curve graph shown represents the waveform used as a reference for determining the drowsiness of the passenger. ​ The waveform shown in region D of the curve graph is an example of the waveform used as a reference for determining the drowsiness of the passenger. The waveform related to region D includes the waveforms related to regions A to C. Region A is the region where the heartbeat interval decreases and is the first period of the descent of the curve graph. Region B occurs after the first period and is the second period where the heartbeat interval increases. Region C occurs after the second period, and the heartbeat interval decreases and then increases. That is, in the third period, the heartbeat interval pulsates. It should be noted that the determination criteria for the passenger's drowsiness in the curve graph of the heartbeat interval with respect to the measurement time are described in Japanese Patent Laid-Open No. 2018-192128.

[0328] In region A, the heartbeat interval decreases. This corresponds to the state where the passenger tries to refrain from closing the eyelids and applies force to the eyelids, etc., and the heart rate increases in order to endure drowsiness. When the heart rate increases, the beats become faster and the heartbeat interval decreases.

[0329] In region B, the heartbeat interval increases. This corresponds to the period when drowsiness is dispelled and then reappears, with a longer heartbeat interval. This is because when the passenger becomes drowsy, the heartbeat interval increases (the heart rate decreases).

[0330] Region C corresponds to the period when drowsiness persists.

[0331] As described above, it is possible to determine the drowsiness of the passenger based on the waveform (region D) in which the region where the passenger wants to consciously or unconsciously resist drowsiness (corresponding to region A) and the region where drowsiness reappears (regions B and C) are continuous.

[0332] The drowsiness omen data DD is the number of detections of the waveform corresponding to region D within a predetermined measurement time, or the cumulative value of the calculated values calculated based on the waveform corresponding to region D within a predetermined measurement time.

[0333] Return to ​ , the calculation unit 113 sends the drowsiness omen data DD to the user interface 118 (an example of a providing device). As the user interface 118, examples include a car navigation system, a smartphone, a smartwatch, a terminal device dedicated to the sensor 110, etc. In this mode, a car navigation system installed in the moving body 102 is adopted.

[0334] The user interface 118 includes both or one of a screen display device (not shown) and a speaker (not shown) for providing a specific service to the passenger. The user interface 118 provides a specific service to the passenger through images or sounds.

[0335] The user interface 118 includes a communication device (not shown) and is connected to a network 158 such as the Internet through this communication device. The user interface 118 sends and receives data to and from the cloud 159 via the network 158.

[0336] The cloud 159 includes a current drowsiness omen data acquisition unit 114, a past drowsiness omen data acquisition unit 115, a state estimation unit 116, and a storage unit 160.

[0337] The current drowsiness omen data acquisition unit 114 acquires the current drowsiness omen data DDA from the user interface 118 via the network 158. The current drowsiness omen data DDA is defined as the drowsiness omen data DD of the passenger in the state of currently riding in the moving body 102.

[0338] The drowsiness omen data DD sent from the user interface 118 to the cloud 159 via the network 158 is acquired by the current drowsiness omen data acquisition unit 114 and sequentially stored in the storage unit 160.

[0339] The past drowsiness omen data acquisition unit 115 acquires the past drowsiness omen data DDB stored in the storage unit 160. The past drowsiness omen data DDB is the drowsiness omen data DD detected when a past passenger boarded the moving body 102.

[0340] Based on the difference between the current drowsiness omen data DDA and the past drowsiness omen data DDB, the state estimation unit 116 estimates the change in the health state of the passenger.

[0341] The storage unit 160 stores the past drowsiness omen data DDB sent via the network 158 from the user interface 118. In addition, the storage unit 160 also stores the drowsiness determination criterion DCA and the comparison condition CC.

[0342] The estimation result related to the drowsiness of the passenger estimated by the state estimation unit 116 is sent to the user interface 118 via the network 158. The estimation result related to the drowsiness of the passenger sent to the user interface 118 is sent to the service providing unit 117. Based on the result of estimating an increase in drowsiness of a person skilled in the art, the service providing unit 117 controls the operation of the navigation system.

[0343] In addition, based on the result of estimating an increase in drowsiness of a person skilled in the art, the service providing unit 117 controls the mobile body safety device 119. The mobile body safety device 119 is not particularly limited and is a device installed in the mobile body 102 to enable the safe movement of the mobile body 102. Examples of the mobile body safety device 119 include an automatic braking system, a throttle control system, a contact detection device for the steering wheel, a drowsiness omen detection system based on an in-vehicle camera, etc.

[0344] 2. Operations of the Embodiment

[0345] 2.1. Main Program

[0346] Next, with reference to ​ this specification, the operations of the drowsiness information providing device 101 of this embodiment will be described. ​ FIG. is a flowchart showing the operations of the drowsiness information providing device 101 of this embodiment. When the drowsiness information providing device 101 is started, the biological signal acquisition process S201 is executed. In the biological signal acquisition process S201, the sensor 110 detects a physical quantity from a passenger sitting on the seat 21 of the moving body 102. The physical quantity detected by the sensor 110 is transmitted to the control circuit 111, and the control circuit 111 calculates the biological signal BS of the passenger based on the physical quantity.

[0347] Next, a heartbeat signal estimation process S202 is executed. In the heartbeat signal estimation process S202, the estimation unit 112 estimates a heartbeat signal HS related to the heartbeat of the passenger based on the biological signal BS acquired from the control circuit 111.

[0348] Next, a drowsiness omen data calculation process S203 is executed. In the drowsiness omen data calculation process S203, the calculation unit 113 calculates drowsiness omen data DD based on the heartbeat signal HS acquired from the estimation unit 112. The calculated drowsiness omen data DD is sent from the user interface 118 to the cloud 159 via the network 158.

[0349] Next, a state estimation process S204 is executed. In the state estimation process S204, the state estimation unit 116 estimates whether the drowsiness of the passenger has increased based on whether the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC.

[0350] Next, a service provision process S205 is executed. In the service provision process S205, the service provision unit 117 controls the provision device for providing a specific service to the passenger based on the situation where it is estimated from the state estimation unit 116 that the drowsiness of the passenger has increased. Specific descriptions are given below.

[0351] The service provision unit 117 can be configured to control the user interface 118 that evokes attention to at least one of vision, hearing, touch, and smell of the passenger.

[0352] In the case where an in-vehicle navigation system is applied as the user interface 118, for example, the following services can be provided. The user interface 118 can, for example, clearly convey to the passenger a message indicating an increase in the passenger's drowsiness by voice or display it on the screen. The message is not particularly limited, and for example, "Your drowsiness is increasing", "It is recommended that you take a rest", etc., and any message can be adopted.

[0353] In addition, the user interface 118 can also emit a warning sound to wake up the passenger.

[0354] In addition, as the user interface 118, for example, in the case where a smartphone, a tablet terminal, or a smartwatch is applied, the service provision unit 117 can also be configured to wake up the passenger by using the vibration of the user interface 118 and utilizing the vibration through the touch of the passenger.

[0355] The service provision unit 117 can also be configured to control the mobile body safety device 119. For example, in the case where an automatic braking system is applied as the mobile body safety device 119, it can be configured to control it in such a way as to increase the sensitivity of the automatic braking and start the deceleration braking in advance.

[0356] In addition, when the throttle control system is applied as the moving body safety device 119, the service providing unit 117 sets an upper limit for the throttle opening degree, suppressing sudden acceleration of the moving body 102 even when the rider suddenly steps on the throttle.

[0357] In addition, when the contact detection device for the steering wheel is applied as the moving body safety device 119, the time interval for detecting the contact of the rider can be shortened. Thereby, the contact state of the rider with the steering wheel is frequently detected, and the rider is frequently warned about the contact with the steering wheel. It can also be configured such that when the rider does not contact the steering wheel even after being warned, the service providing unit 117 quickly transfers to the automatic parking mode by controlling the automatic braking system and the throttle control system, and safely stops the moving body 102.

[0358] In addition, the service providing device can also be configured to vibrate the steering wheel to wake up the rider through vibration.

[0359] In addition, when the drowsiness omen detection system based on the in-vehicle camera is applied as the moving body safety device 119, the service providing unit 117 can also be configured to increase the sensitivity of the camera system to easily issue a warning to the rider.

[0360] When the service providing process S205 ends, the operation of the drowsiness information service providing device 101 ends.

[0361] 2.2. State estimation process

[0362] Next, with reference to ​ , the state estimation process S204 will be described in detail. In this mode, as shown in ​ , as the state estimation process S204, the state estimation process 21 (S210) is executed. ​ The flowchart showing the state estimation process 21 (S210). The state estimation process 21 in this mode is, as will be described in detail later, when the current drowsiness omen data DDA is above the drowsiness determination criterion DCA, it is presumed that the rider's drowsiness has increased. In addition, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA and the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC, it is presumed that the rider's drowsiness has increased.

[0363] The current drowsiness omen data acquisition unit 114 acquires the current drowsiness omen data DDA (S211).

[0364] Next, the past drowsiness omen data acquisition unit 115 acquires the past drowsiness omen data DDB from the storage unit 160 (S212).

[0365] Next, the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213).

[0366] When the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213: Yes), the state estimation unit 116 estimates that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 21 (S210) ends.

[0367] On the other hand, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA (S213: No), the state estimation unit 116 determines whether the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC (S215).

[0368] When the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC (S215: Yes), the state estimation unit 116 estimates that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 21 (S210) ends.

[0369] On the other hand, when the current drowsiness omen data DDA and the past drowsiness omen data DDB do not satisfy the comparison condition CC (S215: No), the state estimation process 21 (S210) ends.

[0370] 3. Effects of this method

[0371] According to this method, based on whether the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy a predetermined comparison condition CC, it is determined whether the drowsiness of the passenger has increased. Therefore, the change in the drowsiness of the passenger over time can be estimated. Thus, compared with the case of making a determination only based on the current information of the passenger, that is, the current drowsiness omen data DDA, the accuracy of estimating the change in the drowsiness of the passenger can be improved.

[0372] For example, assume that in the current drowsiness omen data DDA, the drowsiness omen data DD is observed three times within 10 minutes. On the other hand, assume that in the past drowsiness omen data DDB, the drowsiness omen data DD is observed twice within 10 minutes. In this case, if the past drowsiness omen data DDB is compared with the current drowsiness omen data DDA, the frequency of the drowsiness omen data DD per unit time increases. When the increase in the frequency between the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfies a predetermined comparison condition CC, it can be estimated that the drowsiness of the passenger has increased.

[0373] In addition, in this method, when the current drowsiness prediction data DDA is equal to or greater than the drowsiness determination criterion DCA, it is presumed that the drowsiness of the passenger increases. When the current drowsiness prediction data DDA is less than the drowsiness determination criterion DCA and the current drowsiness prediction data DDA and the past drowsiness prediction data DDB satisfy the comparison condition CC, it is presumed that the drowsiness of the passenger increases. Thus, in this method, services based on two different criteria can be provided to the passenger. Thereby, more detailed services can be provided to the passenger.

[0374] First, when the current drowsiness prediction data DDA is equal to or greater than the drowsiness determination criterion DCA, services based on the increase in drowsiness are provided to the passenger. For example, a warning sound is emitted, or a display such as "Drowsiness is increasing. Please take a rest." is shown or a sound is emitted. Or, control is performed in such a way as to increase the sensitivity of the automatic braking or to start the deceleration braking in advance, or an upper limit is set for the throttle opening, so that even if the passenger suddenly steps on the throttle, a sudden acceleration of the moving body 102 is suppressed. In addition, the contact state of the passenger with the steering wheel is frequently detected, and the passenger is frequently warned about the contact with the steering wheel. It can also be configured that, in the case where the passenger does not contact the steering wheel even after being warned, the service providing unit 117 quickly shifts to the automatic parking mode by controlling the automatic braking system and the throttle control system, and stops the moving body 102 safely.

[0375] On the other hand, when the current drowsiness prediction data DDA is less than the drowsiness determination criterion DCA, it is presumed that the passenger does not have strong drowsiness. However, in this method, even in the above case, when the current drowsiness prediction data DDA and the past drowsiness prediction data DDB satisfy the comparison condition CC, it is also presumed that the drowsiness of the passenger increases. Thus, services based on the increase in drowsiness can be provided to the passenger at a stage before strong drowsiness occurs. For example, a display such as "It is recommended that you take a rest." can be shown or a sound can be emitted. In addition, it can also be configured to increase the sensitivity of the camera system and easily issue a warning to the passenger. In addition, it can also be configured to vibrate the steering wheel and prompt the passenger to wake up through the vibration.

[0376] (Embodiment 2.2)

[0377] Next, with reference to ​ , Embodiment 2.2 will be described. As ​ shown, the difference between this method and Embodiment 2.1 in the storage unit 160 is that a second drowsiness determination criterion DCB is stored.

[0378] In addition, the difference from Embodiment 2.1 is that the state estimation process 22 (S220) is executed instead of the state estimation process 21 (S210) (refer to ​) It should be noted that for the reference numerals used in the drawings after Embodiment 2.2, as long as there is no special indication, the same reference numerals as those used in the already presented embodiments represent the same constituent elements and the like as those in the already presented embodiments.

[0379] Next, with reference to ​ , the state estimation process 22 (S220) will be described. The difference between the state estimation process 22 (S220) of this embodiment and ​ 's state estimation process 21 (S210) is that it performs a step (S221) of determining whether the current drowsiness omen data DDA is equal to or greater than the second drowsiness determination criterion DCB. The same reference numerals are used for the same processes as those in the state estimation process 21 (S210), and repeated descriptions are omitted.

[0380] As ​ shown, when the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC (S215: Yes), the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the second drowsiness determination criterion DCB stored in the storage unit 160 (S221).

[0381] When the current drowsiness omen data DDA is equal to or greater than the second drowsiness determination criterion DCB (S221: Yes), the state estimation unit 116 presumes that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 22 (S220) ends.

[0382] When the current drowsiness omen data DDA is less than the second drowsiness determination criterion DCB (S221: No), the state estimation process 22 (S220) ends.

[0383] According to this embodiment, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA and the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC, the current drowsiness omen data DDA is compared with the second drowsiness determination criterion DCB. Since the second drowsiness determination criterion DCB is less than the drowsiness determination criterion DCA, it is easy to presume that the drowsiness of the passenger has increased. Thus, even when it is presumed according to the drowsiness determination criterion DCA that the drowsiness of the passenger has not increased, when the comparison condition CC is satisfied by relatively comparing the current drowsiness omen data DDA and the past drowsiness omen data DDB, it is possible to presume the change in the drowsiness of the passenger at a level lower than the drowsiness determination criterion DCA, and it is easy to presume that the drowsiness of the passenger has increased. As a result, the safety of the passenger when driving the moving body 102 can be improved.

[0384] (Embodiment 2.3)

[0385] Next, with reference to​ , Description of Embodiment 2.3. As ​ shown, the difference between this embodiment and Embodiment 2.1 is that the past drowsiness omen data DDB includes the previous drowsiness omen data DDC and the penultimate drowsiness omen data DDD.

[0386] In addition, the difference from Embodiment 2.1 is that instead of the state estimation process 21 (S210), the state estimation process 23 (S230) is executed (see ​ ).

[0387] Next, referring to ​ , the state estimation process 23 (S230) will be described. When the state estimation process 23 (S230) is executed, the current drowsiness omen data acquisition unit 114 acquires the current drowsiness omen data DDA (S211).

[0388] Next, the past drowsiness omen data acquisition unit 115 acquires the previous drowsiness omen data DDC from the storage unit 160 (S231). The previous drowsiness omen data DDC is the drowsiness omen data DD calculated based on the heartbeat signal HS when the passenger last boarded the moving body 102.

[0389] Next, the past drowsiness omen data acquisition unit 115 acquires the penultimate drowsiness omen data DDD from the storage unit 160 (S232). The penultimate drowsiness omen data DDD is the drowsiness omen data DD calculated based on the heartbeat signal HS when the passenger penultimately boarded the moving body 102.

[0390] Next, the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213).

[0391] When the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213: Yes), the state estimation unit 116 presumes that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 23 (S230) ends.

[0392] On the other hand, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA (S213: No), the state estimation unit 116 determines whether the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC (S233).

[0393] When the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC (S233: Yes), the state estimation unit 116 determines whether the previous drowsiness omen data DDC is greater than the penultimate drowsiness omen data DDD (S234).

[0394] When the previous drowsiness omen data DDC is greater than the penultimate drowsiness omen data DDD (S234: Yes), the state estimation unit 116 estimates that the drowsiness of the passenger has increased (S214). Thereby, the state estimation process 23 (S230) ends. In this way, when the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC and the previous drowsiness omen data DDC is greater than the penultimate drowsiness omen data DDD, the state estimation unit 116 estimates that the drowsiness of the passenger has increased. That is, the comparison condition CC of this method is that the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC, and the previous drowsiness omen data DDC is greater than the penultimate drowsiness omen data DDD.

[0395] On the other hand, when the current drowsiness omen data DDA is less than or equal to the previous drowsiness omen data DDC (S233: No), the state estimation process 23 (S230) ends.

[0396] In addition, when the drowsiness omen data is less than or equal to the penultimate drowsiness omen data DDD (S234: No), the state estimation process 23 (S230) ends.

[0397] According to this method, when the current drowsiness omen data DDA is less than the drowsiness determination reference DCA, and the current drowsiness omen data DDA, the previous drowsiness omen data DDC, and the penultimate drowsiness omen data DDD satisfy the comparison condition CC, it is estimated that the drowsiness of the passenger has increased. As described above, the comparison condition CC of this method is that the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC, and the previous drowsiness omen data DDC is greater than the penultimate drowsiness omen data DDD. In this way, by using the previous drowsiness omen data DDC and the penultimate drowsiness omen data DDD, the drowsiness determination of the passenger can be performed more precisely.

[0398] (Embodiment 2.4)

[0399] Next, with reference to ​ , Embodiment 2.4 will be described. As ​ shown, in this method, the difference from Embodiment 2.3 is that in the past drowsiness omen data DDB, the long-term drowsiness omen data DDE is provided instead of the penultimate drowsiness omen data DDD.

[0400] In addition, the difference between this method and Embodiment 2.3 is that instead of the state estimation process 23 (S230), the state estimation process 24 (S240) is executed ( ​ ).

[0401] ​Flowchart showing the state estimation process 24 (S240). The difference between the state estimation process 24 (S240) and Embodiment 2.3 is as follows: The past drowsiness omen data acquisition unit 115 performs the process of acquiring long-term drowsiness omen data DDE (S241); the state estimation unit 116 determines whether the previous drowsiness omen data DDC is greater than the long-term drowsiness omen data DDE (S242).

[0402] As ​ shown, when the state estimation process 24 (S240) is executed, S211 and S231 are executed. S211 and S231 are the same processes as in Embodiment 2.3, so repeated descriptions are omitted.

[0403] The past drowsiness omen data acquisition unit 115 acquires the long-term drowsiness omen data DDE (S241). The long-term drowsiness omen data DDE is the drowsiness omen data DD per unit time calculated based on the heartbeat signal HS when the passenger has taken the moving body 102 multiple times in the past.

[0404] Next, the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213).

[0405] When the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213: Yes), the state estimation unit 116 presumes that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 24 (S240) ends.

[0406] On the other hand, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA (S213: No), the state estimation unit determines whether the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC (S233).

[0407] When the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC (S233: Yes), the state estimation unit 116 determines whether the previous drowsiness omen data DDC is greater than the long-term drowsiness omen data DDE (S242).

[0408] When the drowsiness omen data is greater than the long-term drowsiness omen data DDE (S242: Yes), the state estimation unit 116 presumes that the drowsiness of the passenger has increased (S214). Thus, the state estimation process 24 (S240) ends. In this way, when the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC and the previous drowsiness omen data DDC is greater than the long-term drowsiness omen data DDE, the state estimation unit 116 presumes that the drowsiness of the passenger has increased. That is, the comparison condition CC of this method is that the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC, and the previous drowsiness omen data DDC is greater than the long-term drowsiness omen data DDE.

[0409] On the other hand, when the current drowsiness omen data is less than or equal to the previous drowsiness omen data DDC (S233: No), the state estimation process 24 (S240) ends.

[0410] In addition, when the previous drowsiness omen data DDC is less than or equal to the long-term drowsiness omen data DDE (S242: No), the state estimation process 24 (S240) ends.

[0411] According to this method, when the current drowsiness omen data DDA is less than the drowsiness determination reference DCA and the current drowsiness omen data DDA, the previous drowsiness omen data DDC, and the long-term drowsiness omen data DDE satisfy the comparison condition CC, it is presumed that the drowsiness of the passenger increases. As described above, the comparison condition CC of this method is that the current drowsiness omen data DDA is greater than the previous drowsiness omen data DDC, and the previous drowsiness omen data DDC is greater than the long-term drowsiness omen data DDE. In this way, when presuming whether the drowsiness of the passenger increases, by using the long-term drowsiness omen data DDE, it is possible to presume the drowsiness of the passenger in consideration of the relatively long-term health status of the passenger. The following is a detailed description.

[0412] For example, in the drowsiness determination reference DCA, it is assumed that when the drowsiness omen data DD is observed five times within 10 minutes, it is presumed that the drowsiness of the passenger increases. At this time, for example, in the current drowsiness omen data DDA, it is assumed that the state where the drowsiness omen data DD is observed three times within 10 minutes continues. In this case, based on the drowsiness determination reference DCA, it is not presumed that the drowsiness of the passenger increases.

[0413] However, for example, it is assumed that in the past drowsiness omen data DDB one week ago, the drowsiness omen data DD was observed twice within 10 minutes. Then, from last week to this week, the number of observations of the drowsiness omen data DD within 10 minutes increased from two to three. According to this method, the state estimation unit 116 can presume that the drowsiness of the passenger increases. Thus, it is possible to accurately presume the drowsiness of a passenger for whom an increase in drowsiness is not presumed based on the drowsiness determination reference DCA. However, the drowsiness determination reference DCA is not limited to the above value.

[0414] (Embodiment 2.5)

[0415] Next, refer to ​ , and describe Embodiment 2.5. The difference between this method and Embodiment 2.1 is that the state estimation process 25 (S250) is executed instead of the state estimation process 21 (S210).

[0416] In the state estimation process 25 (S250), the difference from the state estimation process 21 (S210) is that instead of​ execute S251 instead of S212, and execute S252 instead of S215. For the same processing as the state estimation process 21 (S210), the same reference numerals are used, and repeated descriptions are omitted. ​ The past drowsiness omen data acquisition unit 115 acquires past drowsiness omen data DDF (S251) for the same time period from the storage unit 160. The past drowsiness omen data DDF for the same time period is drowsiness omen data DD calculated based on the heartbeat signal HS when the passenger was on board the moving body 102 during a past time period including the time when the current drowsiness omen data DDA was measured.

[0417] Describe the past drowsiness omen data DDF for the same time period. For example, consider a case where a passenger using the moving body 102 commutes by taking the moving body 102 from 7:30 to 8:30 every day on weekdays from Monday to Friday. For example, when the current drowsiness omen data DDA is acquired at 8:00 in the morning on Friday, the past drowsiness omen data DDB from 7:30 to 8:30 on Thursday of the previous day can be cited as the past drowsiness omen data DDF for the same time period. In the above example, it is not limited to Thursday of the previous day, and the drowsiness omen data DD measured when the moving body 102 was boarded during the time period including 8:00 in the morning before Friday when the current drowsiness omen data DDA was measured can also be used as the past drowsiness omen data DDF for the same time period. However, the measurement time of the current drowsiness omen data DDA is arbitrary and is not limited to the above time period.

[0418] In this mode, in S252, the state estimation unit 116 determines whether the current drowsiness omen data DDA and the past drowsiness omen data DDF for the same time period satisfy the comparison condition CC. The past drowsiness omen data DDF for the same time period is calculated during a past time period including the time when the current drowsiness omen data DDA was measured. Therefore, the measurement conditions of the past drowsiness omen data DDF for the same time period are more similar compared to the past drowsiness omen data DDB measured during a time period different from the measurement time of the current drowsiness omen data DDA. By relatively comparing the past drowsiness omen data DDF for the same time period measured under relatively similar conditions with the current drowsiness omen data DDA, it is possible to accurately estimate the temporal change in the drowsiness of the passenger from the past to the present.

[0419]

[0420] (Embodiment 2.6)

[0421] ​ Next, with reference to ​ , Embodiment 2.6 will be described. The difference between this mode and Embodiment 2.1 is that instead of ​The state estimation process 21 (S210) executes the state estimation process 26 (S260).

[0422] ​ The flowchart showing the state estimation process 26 (S260). When the state estimation process 26 (S260) is executed, the current drowsiness omen data acquisition unit 114 acquires the current drowsiness omen data DDA (S211).

[0423] Next, the current drowsiness omen data acquisition unit 114 acquires the long-term current drowsiness omen data DDG (S261). The long-term current drowsiness omen data DDG is the drowsiness omen data DD calculated based on the heartbeat signal HS within a predetermined comparison period including the current time. The comparison period is a period longer than the shortest time when acquiring the current drowsiness omen data DDA. As the comparison period, for example, any period such as a single ride time, one day, one week, one month, etc. can be appropriately selected. The period can be selected by the rider or preset in advance.

[0424] Next, the past drowsiness omen data acquisition unit 115 acquires the long-term past drowsiness omen data DDH from the storage unit 160 (S262). The long-term past drowsiness omen data DDH is the drowsiness omen data DD calculated based on the heartbeat signal HS within the comparison period before the current time. Regarding the comparison period, since it is the same as that of the long-term current drowsiness omen data DDG, the repeated description is omitted. In this mode, the comparison period related to the long-term current drowsiness omen data DDG is the same as the comparison period related to the long-term past drowsiness omen data DDH.

[0425] Next, the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213).

[0426] When the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213: Yes), the state estimation unit 116 presumes that the drowsiness of the rider has increased (S214). Thus, the state estimation process 26 (S260) ends.

[0427] On the other hand, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA (S213: No), the state estimation unit 116 determines whether the long-term current drowsiness omen data DDG and the long-term past drowsiness omen data DDH satisfy the comparison condition CC (S263).

[0428] When the long-term current drowsiness omen data DDG and the long-term past drowsiness omen data DDH satisfy the comparison condition CC (S263: Yes), the state estimation unit 116 presumes that the drowsiness of the rider has increased (S214). Thus, the state estimation process 26 (S260) ends.

[0429] On the other hand, when the present drowsiness omen data DDG for a long period and the past drowsiness omen data DDH for a long period do not satisfy the comparison condition CC (S263: No), the state estimation process 26 (S260) ends.

[0430] According to this method, when the present drowsiness omen data DDA is less than the drowsiness determination reference DCA and the increase in the drowsiness of the passenger is not presumed, the long-term present drowsiness omen data DDG is compared with the long-term past drowsiness omen data DDH, and it is presumed whether the drowsiness of a person skilled in the art increases based on whether the comparison condition CC is satisfied. By comparing the long-term present drowsiness omen data DDG with the long-term past drowsiness omen data DDH, it is possible to compare the present drowsiness omen data DDA with the past drowsiness omen data DDB over a relatively long period, and thus it is possible to presume the temporal change in the drowsiness of the passenger from a long-term perspective.

[0431] For example, if the comparison period is set to one ride time, it is possible to presume the change in drowsiness for each ride time. Similarly, it is possible to presume the change in the drowsiness of the passenger during the ride period of each day, each week, and each month. In addition, by setting an arbitrary period, for example, it is possible to presume the change in drowsiness during each work shift period for a passenger engaged in the transportation business. In this way, it is possible to presume the change in the drowsiness of the passenger from a long-term perspective.

[0432] (Embodiment 2.7)

[0433] Next, with reference to ​ , Embodiment 2.7 will be described. The difference between this method and Embodiment 2.1 is that instead of ​ the state estimation process 21 (S210), the state estimation process 27 (S270) is executed.

[0434] ​ The flowchart showing the state estimation process 27 (S270). When the state estimation process 7 (S270) is executed, the present drowsiness omen data acquisition unit 114 acquires the present drowsiness omen data DDA (S271).

[0435] Next, the past drowsiness omen data acquisition unit 115 acquires the long-term past drowsiness omen data DDI from the storage unit 160 (S271). The long-term past drowsiness omen data DDI is the detection frequency or the correlation value of the detection frequency of the drowsiness omen per unit time calculated based on the heartbeat signal HS within a predetermined period longer than the period of the heartbeat signal HS used in the calculation of the present drowsiness omen data DDA. As the predetermined period, any period such as one ride time, one day, one week, or one month can be selected.

[0436] Next, the state estimation unit 116 determines whether the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213).

[0437] When the current drowsiness omen data DDA is equal to or greater than the drowsiness determination criterion DCA (S213: Yes), the state estimation unit 116 estimates that the drowsiness of the passenger has increased (S214). Thereby, the state estimation process 27 (S270) ends.

[0438] On the other hand, when the current drowsiness omen data DDA is less than the drowsiness determination criterion DCA (S213: No), the state estimation unit 116 determines whether the current drowsiness omen data DDA and the long-term past drowsiness omen data DDI satisfy the comparison condition CC (S272).

[0439] When the current drowsiness omen data DDA and the long-term past drowsiness omen data DDI satisfy the comparison condition CC (S272: Yes), the state estimation unit 116 estimates that the drowsiness of the passenger has increased (S214). Thereby, the state estimation process 27 (S270) ends.

[0440] On the other hand, when the current drowsiness omen data DDA and the long-term past drowsiness omen data DDI do not satisfy the comparison condition CC (S272: No), the state estimation process 27 (S270) ends.

[0441] According to this method, based on whether the current drowsiness omen data DDA and the long-term drowsiness omen data measured within a predetermined period longer than the current drowsiness omen data DDA satisfy the comparison condition CC, it is estimated whether the drowsiness of the passenger has increased. For example, the predetermined period is set to one week. In this case, for example, in the current drowsiness omen data DDA of the passenger, the drowsiness omen data DD is observed three times in 10 minutes. On the other hand, in the long-term past drowsiness omen data DDI, when the unit time is set to 10 minutes, it is set that the drowsiness omen data DD is observed twice in 10 minutes. Thus, it can be known that the drowsiness of the passenger has changed in the increasing direction compared with last week. Thereby, it is possible to estimate the change in the drowsiness of the passenger based on the change in the drowsiness of the passenger over a long period of time.

[0442] (Embodiment 2.8)

[0443] Next, Embodiment 2.8 will be described. When it is estimated that the drowsiness of the passenger has increased, the service providing unit 117 of this method controls the providing device in such a way that the period for providing services to the passenger is advanced. Thereby, it is possible to provide services suitable for the change in the drowsiness of the passenger. The rest is substantially the same as Embodiment 2.1, so the same reference numerals are assigned to the same components, and repeated descriptions are omitted. Hereinafter, refer to ​ for the description.

[0444] For example, in the drowsiness determination criterion DCA, it is assumed that when five drowsiness omen data DD are observed within 10 minutes, it is presumed that the drowsiness of the passenger increases. At this time, for example, in the current drowsiness omen data DDA, it is assumed that the state of observing three drowsiness omen data DD within 10 minutes continues. In this case, based on the drowsiness determination criterion DCA, it is not presumed that the drowsiness of the passenger increases (S213: No).

[0445] However, when the current drowsiness omen data DDA and the past drowsiness omen data DDB satisfy the comparison condition CC (S215: Yes), it is presumed that the drowsiness of the passenger increases (S214).

[0446] Then, the service providing unit 117, for example, decreases the value of the drowsiness determination criterion DCA. As a result, the state estimation unit 116 can easily estimate the drowsiness of the passenger. Consequently, compared with the state before the drowsiness determination criterion DCA becomes smaller, the period in which the providing device provides services to the passenger is advanced. Then, for example, a message indicating an increase in drowsiness can be quickly provided to the passenger through screen display or sound, and thus, the safety of the moving body 102 can be improved. However, the drowsiness determination criterion DCA is not limited to the above value.

[0447] The present disclosure is not limited to the above-described embodiments, and within the scope not departing from the gist thereof, it can be applied to the following modes, for example.

[0448] (2.1) In Embodiment 2.1, the sensor 110 is configured to be installed on the seat 21, and the biological signal BS is acquired based on the change in the body movement of the passenger sitting on the seat 21. However, it is not limited thereto, and the sensor 110 may also emit light (infrared rays, ultraviolet rays, laser, visible light, etc.), sound, etc. to the passenger and detect the reflection from the passenger. In addition, it may be a Doppler sensor that emits microwaves to the passenger and detects the change in the body movement of the passenger based on the difference between the emitted frequency and the received frequency, and any sensor 110 can be appropriately selected.

[0449] (2.2) In Embodiment 2.1, the sensor 110 is configured to be installed inside the seat seat surface portion 22a. However, it is not limited thereto, as shown in ​ the sensor 110 may also be configured to place a component separated from the seat 21 on the upper surface of the seat seat surface portion 22a and install it on the seat seat surface portion 22a by known installation means such as a rubber band, a belt, etc. In addition, the sensor 110 may also be configured to be installed on the seat back surface portion 22b by known installation means such as a rubber band, a belt, etc.

[0450] (2.3) In Embodiment 2.1, the user interface 118 is an in-vehicle navigation system assembled in the mobile body 102, but is not limited thereto. As shown in ​ , it may also be a smartphone, a tablet terminal, a smartwatch, a dedicated terminal, etc., which are separate from the mobile body 102. It should be noted that in ​ , the data stored in the storage unit 160 is omitted. According to this embodiment, the passenger can receive the provision of specific services from the user interface 118 fixed to a holder (not shown) installed in the compartment of the mobile body 102. For example, a message regarding the passenger's health status may be transmitted to the passenger through an image or sound, or guidance and routes of sports facilities, etc. may be displayed. ​ As shown, it may also be a smartphone, a tablet terminal, a smartwatch, a dedicated terminal, etc. that are separate from the mobile body 102. It should be noted that in ​ , the data stored in the storage unit 160 is omitted. According to this embodiment, the passenger can receive the provision of specific services from the user interface 118 fixed to a holder (not shown) installed in the compartment of the mobile body 102. For example, a message regarding the passenger's health status may be transmitted to the passenger through an image or sound, or guidance and routes of sports facilities, etc. may be displayed. ​ in which the data stored in the storage unit 160 is omitted. According to this embodiment, the passenger can receive the provision of specific services from the user interface 118 fixed to a holder (not shown) installed in the compartment of the mobile body 102. For example, a message regarding the passenger's health status may be transmitted to the passenger through an image or sound, or guidance and routes of sports facilities, etc. may be displayed.

[0451] (2.4) In Embodiment 2.1, the user interface 118 transmits or receives information between the cloud 159 via the network 158, but is not limited thereto. As shown in ​ , the configuration of Embodiment 2.1 arranged in the cloud 159 may also be assembled in the mobile body 102 as the control device 162. ​ As shown, the configuration of Embodiment 2.1 arranged in the cloud 159 may also be assembled in the mobile body 102 as the control device 162.

[0452] (2.5) In Embodiment 2.1, the user interface 118 transmits or receives information between the cloud 159 via the network 158, but is not limited thereto. As shown in ​ , it may also be configured such that the ECU 157 transmits the drowsiness omen data DD to the cloud 159 via the network 158, and the user interface 118 (for example, an in-vehicle navigation system) assembled in the mobile body 102 provides information to the passenger. ​ As shown, it may also be configured such that the ECU 157 transmits the drowsiness omen data DD to the cloud 159 via the network 158, and the user interface 118 (for example, an in-vehicle navigation system) assembled in the mobile body 102 provides information to the passenger.

[0453] (2.6) In Embodiment 2.1, the user interface 118 transmits or receives information between the cloud 159 via the network 158, but is not limited thereto. As shown in ​ , it may also be configured such that the ECU 157 transmits the drowsiness omen data DD to the cloud 159 via the network 158, and the user interface 118 (for example, a smartphone, a tablet terminal, a smartwatch) separate from the mobile body 102 provides information to the passenger. ​ As shown, it may also be configured such that the ECU 157 transmits the drowsiness omen data DD to the cloud 159 via the network 158, and the user interface 118 (for example, a smartphone, a tablet terminal, a smartwatch) separate from the mobile body 102 provides information to the passenger.

[0454] (2.7) The ECU 157 of Embodiment 2.1 is configured to include the calculation unit 113, but is not limited thereto. As shown in ​ , it may also be configured such that the cloud 159 includes the calculation unit 113. At this time, it may also be configured such that the user interface 118 (for example, an in-vehicle navigation system) assembled in the mobile body 102 transmits or receives information to / from the cloud 159 via the network 158. ​ As shown, it may also be configured such that the cloud 159 includes the calculation unit 113. At this time, it may also be configured such that the user interface 118 (for example, an in-vehicle navigation system) assembled in the mobile body 102 transmits or receives information to / from the cloud 159 via the network 158.

[0455] (2.8) The ECU 157 of Embodiment 2.1 is configured to include the calculation unit 113, but is not limited thereto. As shown in ​ ​As shown, it may also be configured such that the cloud 159 includes a calculation unit 113. In this case, it may also be configured such that a user interface 118 (e.g., a smartphone, a tablet terminal, a smartwatch, a dedicated terminal) separate from the mobile body 102 transmits or receives information to and from the cloud 159 via the network 158.

[0456] (2.9) The mobile body 102 of Embodiment 2.1 is configured to include an estimation unit 112 and a calculation unit 113, but is not limited thereto. As ​ shown, it may also be configured such that the cloud 159 includes an estimation unit 112 and a calculation unit 113. In this case, it may also be configured such that a user interface 118 (e.g., a car navigation system) assembled in the mobile body 102 transmits or receives information to and from the cloud 159 via the network 158.

[0457] (2.10) The mobile body 102 of Embodiment 2.1 is configured to include an estimation unit 112 and a calculation unit 113, but is not limited thereto. As ​ shown, it may also be configured such that the cloud 159 includes an estimation unit 112 and a calculation unit 113, and a user interface 118 (e.g., a smartphone, a tablet terminal, a smartwatch, a dedicated terminal) separate from the mobile body 102 transmits or receives information to and from the cloud 159 via the network 158.

Claims

1. A health information service providing device (10) for a mobile body user, wherein, the health information service providing device (10) for a mobile body user includes: an acquisition device (56) that acquires a biological signal (BS) of a mobile body user riding on a mobile body (11); an estimation unit (13) that estimates a heartbeat signal (HS) related to the heartbeat of the mobile body user based on the biological signal; a calculation unit (14) that calculates VLF data (VD) related to an extremely low frequency component of 0.0033 to 0.04 Hz based on the heartbeat signal; a current VLF data acquisition unit (15) that acquires current VLF data (VDA), where the current VLF data (VDA) is the VLF data of the current mobile body user, and the current includes the current ride time when currently riding or the most recent ride time when not currently riding; a past VLF data acquisition unit (16) that acquires past VLF data (VDB), where the past VLF data (VDB) is a statistical representative value that is a representative value of counts or positions of the VLF data within a specific period in the past compared to the current; a state estimation unit (17) that estimates a change in the health state of the mobile body user based on the difference between the current VLF data and the past VLF data; and a service providing unit (18) that provides a specific service to the mobile body user based on the change in the health state of the mobile body user.

2. The health information service providing apparatus for a mobile body user according to claim 1, wherein, The current VLF data is a statistical representative value of the VLF data during a period that includes at least a part of the current ride when currently riding.

3. The health information service providing apparatus for a mobile body user according to claim 1, wherein, The current VLF data is a statistical representative value of the VLF data during a period that includes at least a part of the most recent ride when not currently riding.

4. The health information service providing device for a mobile body user according to claim 1, wherein, the past VLF data includes: first past VLF data (VDF), where the first past VLF data (VDF) is a statistical representative value of the VLF data within a specific period that is one or more times earlier than the current; and second past VLF data (VDG), where the second past VLF data (VDG) is a statistical representative value of the VLF data within a specific period that is one or more times earlier than the period of the first past VLF data, and the state estimation unit estimates a change in the health state of the mobile body user based on the result of comparing the current VLF data and the first past VLF data according to a predetermined first comparison criterion (TVA, TVJ) and the result of comparing the current VLF data and the second past VLF data according to a predetermined second comparison criterion (TVA, TVK).

5. The health information service providing device for a mobile body user according to claim 4, wherein, When a first past difference value (ΔDVA) obtained by subtracting the current VLF data from the first past VLF data is equal to or greater than a threshold value (TVA) which is an example of the first comparison reference, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction. Furthermore, when the first past difference value is less than the threshold value, and a second past difference value (ΔDVB) obtained by subtracting the current VLF data from the second past VLF data is equal to or greater than the threshold value which is an example of the second comparison reference, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

6. The health information service providing device for a mobile body user according to claim 4, wherein when a first past difference value obtained by subtracting the current VLF data from the first past VLF data is equal to or greater than a first past threshold value (TVJ) which is an example of the first comparison reference, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction. Furthermore, when the first past difference value is less than the first past threshold value, and the second past difference value obtained by subtracting the current VLF data from the second past VLF data is greater than the first past threshold value and equal to or greater than a second past threshold value (TVK) which is an example of the second comparison reference, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

7. The health information service providing device for a mobile body user according to claim 5 or 6, wherein the current VLF data is the VLF data at the current boarding or the most recent boarding. the first past VLF data is the statistical representative value of the VLF data at a boarding earlier than the current boarding or the most recent boarding by at least one time. the second past VLF data is the statistical representative value of the VLF data at a boarding earlier than the boarding time of the first past VLF data by at least one time.

8. The health information service providing device for a mobile body user according to claim 5 or 6, wherein the current VLF data is the VLF data at the current boarding or the most recent boarding. the first past VLF data is the statistical representative value of the VLF data at a boarding at least one day earlier than the time when the current VLF data is measured and including the same time as the time when the current VLF data is measured. the second past VLF data is the statistical representative value of the VLF data at a boarding at least one day earlier than the boarding time of the first past VLF data and including the same time as the time when the current VLF data is measured.

9. The health information service providing device for a mobile body user according to claim 5 or 6, wherein the current VLF data is the VLF data at the current boarding or the most recent boarding. The first past VLF data is the statistical representative value of the VLF data within a predetermined period before the current ride or the most recent ride. The second past VLF data is the statistical representative value of the VLF data within the predetermined period before the first past VLF data.

10. The service providing device according to claim 5, wherein the threshold value includes a normal threshold value (TVE) and a warning threshold value (TVF), and the warning threshold value (TVF) is a value smaller than the normal threshold value. When the current VLF data is greater than a specific threshold value (TVD), the state estimation unit uses the normal threshold value. When the current VLF data is less than or equal to the specific threshold value, the state estimation unit uses the warning threshold value.

11. The service providing device according to claim 6, wherein the first past threshold value includes a first past normal threshold value (TVL) and a first past warning threshold value (TVM), and the first past warning threshold value (TVM) is a value smaller than the first past normal threshold value. the second past threshold value includes a second past normal threshold value (TVN) and a second past warning threshold value (TVO), and the second past warning threshold value (TVO) is a value smaller than the second past normal threshold value. When the current VLF data is greater than the specific threshold value, the state estimation unit uses the first past normal threshold value and the second past normal threshold value. When the current VLF data is less than or equal to the specific threshold value, the state estimation unit uses the first past warning threshold value and the second past warning threshold value.

12. The health information service providing device for a mobile body user according to claim 1, wherein the current VLF data is the VLF data of the ride volume at the current ride or the most recent ride. the past VLF data is the statistical representative value of the VLF data of the ride volumes in a past predetermined period. When the difference value obtained by subtracting the current VLF data from the past VLF data is equal to or greater than the threshold value, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

13. The health information service providing device for a mobile body user according to claim 1, wherein the current VLF data is the VLF data at the current ride or the most recent ride. the past VLF data is the statistical representative value of the VLF data of the past ride at the same time as the time when the current VLF data is measured. When the same-time period difference value obtained by subtracting the current VLF data from the past VLF data is equal to or greater than the same-time period threshold value, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

14. The service providing device according to claim 1, wherein The present VLF data is the statistical representative value of the VLF data during a predetermined comparison period of the current ride or the most recent ride. The past VLF data is the statistical representative value of the VLF data during the comparison period before the current ride or the most recent ride. When the period difference value obtained by subtracting the present VLF data from the past VLF data is equal to or greater than the period threshold value, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

15. The health information service providing apparatus for a mobile body user according to claim 1, wherein, The state estimation unit estimates the change in the health state of the mobile body user based on the trend of the VLF data from the past to the present obtained from a plurality of the past VLF data and the present VLF data.

16. The health information service providing device for a mobile body user according to claim 15, wherein The trend includes both or either of a state in which the plurality of the past VLF data monotonically decreases to the present VLF data and a state in which the plurality of the past VLF data repeatedly decreases and increases cyclically to the present VLF data.

17. The health information service providing device for a mobile body user according to claim 1, wherein The present VLF data is the VLF data of the current ride or the most recent ride. The past VLF data includes: First past period VLF data (VDC), which is the statistical representative value of the VLF data during a first period before the current ride or the most recent ride; And Second past period VLF data (VDD), which is the statistical representative value of the VLF data during a second period longer than the first period of the first past period VLF data. The state estimation unit estimates the health state of the mobile body user by comprehensively considering the comparison result between the first past period VLF data and the present VLF data and the comparison result between the second past period VLF data and the present VLF data.

18. The health information service providing device for a mobile body user according to claim 17, wherein When the first difference value (ΔDVF) obtained by subtracting the present VLF data from the first past period VLF data is equal to or greater than a first threshold value (TVG) and the second difference value obtained by subtracting the present VLF data from the second past period VLF data is equal to or greater than a second threshold value, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

19. The health information service providing device for a mobile body user according to claim 17, wherein When the first difference value obtained by subtracting the present VLF data from the first past period VLF data is equal to or greater than the first threshold value, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction. Furthermore, when the first difference value is less than the first threshold value and a second difference value (ΔDVG) obtained by subtracting the current VLF data from the VLF data in the second past period is equal to or greater than a second threshold value (TVH), the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

20. The apparatus for providing health information service for a mobile body user according to claim 1, wherein the apparatus for providing health information service for a mobile body user further includes a minimum VLF data acquisition unit (61) that acquires minimum VLF data (VDE), and the minimum VLF data (VDE) is the minimum value of the VLF data during a period longer than the past specific period in the past VLF data. The state estimation unit estimates a change in the health state of the mobile body user based on the difference between the current VLF data and the past VLF data. When the current VLF data is less than the minimum VLF data, the state estimation unit estimates that the health state of the mobile body user has changed in an adverse direction.

21. The apparatus for providing health information service for a mobile body user according to claim 1, wherein The state estimation unit estimates a change in the health state of the mobile body user based on the difference between the current VLF data and the past VLF data. When the current VLF data is equal to or less than an emergency threshold value (TVI), it is estimated that the health state of the mobile body user has changed in an adverse direction.

22. An apparatus for providing health information service for a passenger, wherein the apparatus for providing health information service for a passenger includes: an acquisition device (156) that acquires a biological signal (BS) of a passenger when the passenger is on board a mobile body (102); an estimation unit (112) that estimates a heartbeat signal (HS) related to the heartbeat of the passenger based on the biological signal; a calculation unit (113) that calculates drowsiness omen data (DD) based on the heartbeat signal, and the drowsiness omen data (DD) is data related to the drowsiness omen of the passenger and is the number of detections of the drowsiness omen per unit time measured within a predetermined measurement time or a related value of the number of detections; a current drowsiness omen data acquisition unit (114) that acquires current drowsiness omen data (DDA), and the current drowsiness omen data (DDA) is the drowsiness omen data of the passenger in the state of being currently on board the mobile body; a past drowsiness omen data acquisition unit (115) that acquires past drowsiness omen data (DDB), and the past drowsiness omen data (DDB) is the drowsiness omen data detected when the passenger was on board the mobile body in the past; a state estimation unit (116) that estimates whether the drowsiness of the passenger has increased based on whether the current drowsiness omen data and the past drowsiness omen data satisfy a predetermined comparison condition (CC); and A service providing unit (117) that controls providing devices (118, 119) for providing a specific service to the passenger based on a presumption that the drowsiness of the passenger has increased.

23. The passenger health information service providing device according to claim 22, wherein when the current drowsiness omen data is equal to or greater than a drowsiness determination criterion (DCA), the state presumption unit presumes that the drowsiness of the passenger has increased. Furthermore, when the current drowsiness omen data is less than the drowsiness determination criterion and the current drowsiness omen data and the past drowsiness omen data satisfy the comparison condition, the state presumption unit presumes that the drowsiness of the passenger has increased.

24. The passenger health information service providing device according to claim 22, wherein when the current drowsiness omen data is equal to or greater than a drowsiness determination criterion, the state presumption unit presumes that the drowsiness of the passenger has increased. Furthermore, when the current drowsiness omen data is less than the drowsiness determination criterion, the current drowsiness omen data and the past drowsiness omen data satisfy the comparison condition, and the current drowsiness omen data is equal to or greater than a second drowsiness determination criterion (DCB) that is less than the drowsiness determination criterion, the state presumption unit presumes that the drowsiness of the passenger has increased.

25. The passenger health information service providing device according to claim 23 or 24, wherein the current drowsiness omen data is the drowsiness omen data calculated based on the heartbeat signal of the passenger when currently riding in the moving body, the past drowsiness omen data includes: the previous drowsiness omen data (DDC), which is the drowsiness omen data calculated based on the heartbeat signal of the passenger when the passenger previously rode in the moving body; and the penultimate drowsiness omen data (DDD), which is the drowsiness omen data calculated based on the heartbeat signal of the passenger when the passenger penultimately rode in the moving body, and the comparison condition is that the current drowsiness omen data is greater than the previous drowsiness omen data and the previous drowsiness omen data is greater than the penultimate drowsiness omen data.

26. The passenger health information service providing device according to claim 23 or 24, wherein the current drowsiness omen data is the drowsiness omen data calculated based on the heartbeat signal when currently riding in the moving body, the past drowsiness omen data includes: the previous drowsiness omen data, which is the drowsiness omen data calculated based on the heartbeat signal of the passenger when the passenger previously rode in the moving body; and long-term drowsiness omen data (DDE), which is the drowsiness omen data per unit time calculated based on the heartbeat signals of the passenger when the passenger has ridden in the moving body multiple times in the past. The comparison condition is that the current drowsiness omen data is greater than the previous drowsiness omen data and the previous drowsiness omen data is greater than the long-term drowsiness omen data.

27. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein the past drowsiness omen data is the drowsiness omen data calculated based on the heartbeat signal when the rider was on board the moving body during a past time period including the time when the current drowsiness omen data was measured.

28. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein the current drowsiness omen data is the drowsiness omen data calculated based on the heartbeat signal during a predetermined comparison period including the current time, and the past drowsiness omen data is the drowsiness omen data calculated based on the heartbeat signal during the comparison period before the current time.

29. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein when it is presumed that the rider's drowsiness increases, the service providing unit controls the providing device in such a way that the period for providing the service to the rider is advanced.

30. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein the past drowsiness omen data is the detection frequency per unit time of the drowsiness omen or the correlation value of the detection frequency calculated based on the heartbeat signal during a predetermined period whose time is longer than the period of the heartbeat signal used to calculate the current drowsiness omen data.

31. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein the service providing unit controls a device that evokes attention to at least one of vision, hearing, touch, and smell of the rider as the providing device.

32. The device for providing a rider's health information service according to any one of claims 22 to 24, wherein the service providing unit controls a mobile body safety device (119) associated with the safety of the mobile body as the providing device.

Images