Automobile user health and behavior monitoring system and method based on Internet of vehicles data informatization

文档序号：791224 发布日期：2021-04-13 浏览：18次中文

阅读说明：本技术 一种基于车联网数据信息化的汽车用户健康、行为监测系统及方法 (Automobile user health and behavior monitoring system and method based on Internet of vehicles data informatization ) 是由叶飞沈千保蒋伟于 2021-01-19 设计创作，主要内容包括：本发明提供一种基于车联网数据信息化的汽车用户健康、行为监测系统及方法,包括依次连接的信息采集模块、传输模块、控制处理模块、预警模块；所述信息采集模块,用于采集信号源信息,所述信号源信息包括被测对象生理参数以及行为信息；所述传输模块,用于将信息采集模块采集到的信号源信息传输至控制处理模块；所述控制处理模块,用于基于预设的驾驶耐久指数,生成预设的系统预警阈值状态集；根据所述信号源信息更新修正被测对象的驾驶耐久指数,并同步生成修正的系统预警阈值状态集；比对信号源信息及驾驶耐久指数是否超出系统预警阈值状态集,得到判断结果；并将判断结果传输至预警模块。所述预警模块,用于根据控制处理模块的判断结果进行声、光和/或振动预警；优点在于,关注驾驶员健康状况、精神状态、行为状况,其在驾驶疲劳监测更注重提前的预警,提前帮助驾驶员关注到不必要的疲劳驾驶风险以进行规避。(The invention provides an automobile user health and behavior monitoring system and method based on Internet of vehicles data informatization, which comprises an information acquisition module, a transmission module, a control processing module and an early warning module which are connected in sequence; the information acquisition module is used for acquiring signal source information, wherein the signal source information comprises physiological parameters and behavior information of a measured object; the transmission module is used for transmitting the signal source information acquired by the information acquisition module to the control processing module; the control processing module is used for generating a preset system early warning threshold state set based on a preset driving endurance index; updating and correcting the driving endurance index of the tested object according to the signal source information, and synchronously generating a corrected system early warning threshold state set; comparing whether the signal source information and the driving endurance index exceed a system early warning threshold state set to obtain a judgment result; and transmitting the judgment result to the early warning module. The early warning module is used for carrying out sound, light and/or vibration early warning according to the judgment result of the control processing module; the method has the advantages that the health condition, the mental state and the behavior condition of the driver are concerned, the early warning is more concerned in the driving fatigue monitoring, and the driver is helped to pay attention to the unnecessary fatigue driving risk in advance to avoid.)

1. A vehicle user health and behavior monitoring system based on vehicle networking data informatization is characterized by comprising an information acquisition module, a transmission module, a control processing module and an early warning module which are sequentially connected;

the information acquisition module is used for acquiring signal source information, wherein the signal source information comprises physiological parameters and behavior information of a measured object;

the transmission module is used for transmitting the signal source information acquired by the information acquisition module to the control processing module;

the control processing module is used for generating a preset system early warning threshold state set based on a preset driving endurance index; updating and correcting the driving endurance index of the tested object according to the signal source information, and synchronously generating a corrected system early warning threshold state set; comparing whether the signal source information and the driving endurance index exceed a system early warning threshold state set to obtain a judgment result; and transmitting the judgment result to the early warning module;

and the early warning module is used for carrying out sound, light and/or vibration early warning according to the judgment result of the control processing module.

2. The system for monitoring health and behavior of users of automobiles according to claim 1, wherein the preset driving endurance index is obtained based on a sleep data state set of a tested object before driving, a recovery data state set of a tested object during short-term rest or relaxation training, a historical data statistical state set of a tested object, a real world big data statistical state set, an integrated model state set of real world big data and personalized data, or one or more of the above-mentioned obtaining.

3. The system for monitoring the health and behavior of the users of the automobiles based on the data informatization of the internet of vehicles as claimed in claim 1, wherein the preset driving endurance index is configured for the tested object in a self-defined manner.

4. The vehicle networking data informatization-based automobile user health and behavior monitoring system according to claim 2 or 3, wherein the information acquisition module comprises a non-contact acquisition module;

the non-contact acquisition module is used for acquiring the physiological parameters and/or behavior information of the tested object to obtain the driving endurance index of the tested object.

5. The system for monitoring the health and behavior of the automobile user based on the data informatization of the Internet of vehicles is characterized in that the non-contact acquisition module is a vibration sensor which is arranged in a stress area below the hip and/or a stress area behind the hip in a non-contact manner with the measured object, the vibration sensor is used for acquiring behavior information of the measured object and transmitting the behavior information to the control processing module, the behavior information comprises driving duration of the measured object and a posture information index, and the posture information index of the measured object is generated by one or more of sitting posture state, sitting posture abnormal value and sitting posture abnormal state duration value.

6. The system for monitoring health and behavior of users of automobiles according to claim 5, wherein said control processing module comprises: the model generation module is used for judging the driving endurance state of the tested object according to the received signal source information and generating a personalized driving endurance index model of the tested object, and the personalized driving endurance index model is configured to generate a corrected system early warning threshold state set for the transition from the waking state to the fatigue state of the tested object;

the data processing module is used for receiving the behavior information, carrying out primary processing on the behavior information and calculating the driving endurance index of the tested object according to the processed behavior information; wherein the preliminary processing comprises filtering, amplifying and A/D conversion;

and the data comparison module is used for updating and correcting the driving endurance index according to the received signal source information, synchronously generating a corrected system early warning threshold state set, judging the fatigue state of the tested object and obtaining a judgment result.

7. The vehicle networking data informatization-based automobile user health and behavior monitoring system according to claim 6, wherein the transmission module comprises:

and the Bluetooth module is used for receiving the judgment result obtained by the control processing module and transmitting the judgment result to the early warning module.

8. The vehicle networking data informatization-based automobile user health and behavior monitoring system according to claim 1, wherein the early warning module comprises:

the display module is used for displaying a visual alarm interface of the driving endurance state and behavior of the object to be tested;

the vibration module is used for realizing vibration of the driver seat;

and the voice module is used for playing the prerecorded audio signal.

9. The vehicle networking data informatization-based automobile user health and behavior monitoring system according to claim 8, wherein the vibration module comprises a voltage stabilization driving circuit and a vibration motor which are sequentially connected, and vibration of different frequencies can be realized.

10. The system for monitoring health and behavior of automobile users based on Internet of vehicles data informatization according to claim 5, characterized in that the vibration sensor is a sensor which equivalently converts physical quantities on the basis of acceleration, pressure, speed and displacement, and comprises an optical fiber sensor.

11. The vehicle networking data informatization-based automobile user health and behavior monitoring system of claim 5, wherein the vibration sensor further comprises: the physiological acquisition module is used for acquiring physiological parameters of a to-be-detected object; the physiological parameters include heart rate, heart rate variability, breathing rate, breathing pattern, stress index, fatigue index.

12. The vehicle networking data informatization-based automobile user health and behavior monitoring system according to claim 5, wherein the physiological acquisition module is a bracelet-worn device, comprising:

the optical heart rate sensor is used for measuring light transmittance data in blood of a to-be-detected object and transmitting the data to the DA14580 chip; the DA14580 chip is used for preprocessing the light transmittance data, performing analog-to-digital conversion through an ADC module arranged in the chip and then calculating the heart rate of an object to be detected; the preprocessing comprises filtering and denoising.

13. A vehicle user health and behavior monitoring method based on vehicle networking data informatization is characterized by comprising the following steps:

step 1, signal source information is collected by an information collection module, wherein the signal source information comprises physiological parameters and behavior information of an object to be detected;

step 2, transmitting the signal source information acquired in the step 1 to a control processing module through a transmission module;

step 3, the control processing module judges the fatigue state of the object to be detected according to the signal source information;

and 4, transmitting the fatigue state result obtained in the step 3 to an early warning module, and carrying out corresponding sound, light and/or vibration early warning by the early warning module according to the fatigue state result.

14. The vehicle networking data informatization-based vehicle user health and behavior monitoring method according to claim 13, wherein the control processing module in step 3 judges the fatigue state of the object to be detected according to the signal source information, specifically: step 3-1, generating a preset system early warning threshold state set based on a preset driving endurance index DEI (t0), wherein the preset system early warning threshold state set comprises: starting early warning state information WarningStatus [ X (T0) ] = WarningStatus [ [ X1(T0), X2(T0), X3(T0), …, xn (T0) ] T ] with respect to a parameter X = [ X1, X2, X3, …, xn ] T; (ii) an early warning state curve, warnengstatus [ DEI (t) ], about DEI changes over time; step 3-2, monitoring the parameter X = [ X1, X2, X3, …, xn ] T during driving, and obtaining a modified driving endurance index DEI [ (X, T) = DEI [ ] about the parameter X changing along with time (X1, X2, X3, …, xn ] T, T); step 3-3, updating warning threshold state information WarningStatus [ X (T) ] = WarningStatus [ X1(T), X2(T), X3(T), …, xn (T) ] T ] regarding the parameter X = [ X1, X2, X3, …, xn ] T based on the corrected driving endurance index DEI [ (X, T) ]; and 3-4, the updated system early warning threshold state set comprises two parts: WarningStatus [ [ x1(T), x2(T), x3(T), …, xn (T) ] T ]. U.WarningStatus [ DEI (T) ]; step 3-5, judging an early warning time point T1 according to DEI (X, T) and WarningStatus (DEI (T)); step 3-6, judging an early warning time point T2[ X ] = [ T2(X1), T2(X2), T2(X3), … and T2(xn) ] according to X (T) and WarnngStatus [ X (T); and 3-7, starting early warning at the earliest occurrence of any early warning time point according to the early warning time points of T1 and T2.

15. The vehicle networking data informatization-based automobile user health and behavior monitoring method according to claim 14, wherein the control processing module judges the fatigue state of the object to be detected according to signal source information, wherein the signal source information comprises parameters X, and X is one or more of driving time, sitting posture state, heart rate variability, respiratory rate, respiratory pattern, mental stress index and fatigue index.

16. The vehicle networking data informatization-based vehicle user health and behavior monitoring method according to claim 13, wherein the control processing module in step 3 judges the fatigue state of the object to be detected according to the signal source information, specifically: step 3-1, generating a preset system early warning threshold state set by a preset driving endurance index: setting a preset value of a current driving endurance index of a tested object in a self-defined configuration as DEI (t0), automatically generating a preset system early warning threshold state set WarningStatus (t0) matched with the preset value according to the preset value, and defining driving endurance index loss delta DEI based on single continuous driving time OCDT (t0) -delta DEI (t), delta DEI (t) = g (ODT (t)); as the duration of a single continuous driving increases, the corresponding system early warning threshold state sets warnengstatus (DEI, OCDT), DEI (t) = DEI (t0) - (a2 ^ odt (t) ^2 + a1 ^ odt (t) + a0), δ DEI (t) = g (odt (t) = a2 ^ odt (t) ^2 + a1 ^ odt (t) + a 0); in the formula, WarningStatus [ DEI ] is a system early warning threshold state of a driving endurance index, and WarningStatus [ ODT ] is a system early warning threshold state set of single continuous driving time;

DEI (t) is below a WarningStatus [ DEI ] defined threshold based on a t1 time point; or when ODT (t) exceeds a WarnngStatus [ ODT ] defined threshold based on a t2 time point; namely, at the time point of t1, a judgment result is obtained and is transmitted to the early warning module;

WarningStatus (DEI, OCDT) is a system early warning threshold state set generated according to a driving endurance index DEI (t 0);

step 3-2, further, generating a driving endurance index of the tested object according to the signal source information, and synchronously generating a corrected system early warning threshold state set: based on the driving endurance index DEI and the single continuous driving time OCDT parameter change, a corresponding system early warning threshold state set WarningStatus (t) is a variable state set;

WarnngStatus [ DEI ] is gradually corrected to WarningStatus [ DEI ] along with the single-driving duration OCDT; the WarningStatus [ ODT ] is gradually corrected to WarningStatus [ ODT ] along with the driving endurance index;

based on t1 time point, dei (t) is below the warnengstatus [ dei (t)) ] defining threshold, or based on t2 time point, odt (t) exceeds the warnengstatus [ odt (t)) ] defining threshold; that is, at time t1, a judgment result is obtained, and the judgment result is transmitted to the early warning module.

17. The method for monitoring health and behavior of a vehicle user based on vehicle networking data informatization according to claim 16, wherein the step 3-2' further comprises setting physiological parameters HR of the measured object based on the change of heart rate HR, and obtaining modified DEI (t) = DEI (t0) - (A2) = ODT (t) ^2 + A1 ^ ODT (t) + A0) -f (HR), wherein f and A are fitting functions;

as time progresses, WarningStatus [ OCDT [ () ]) is a modified set of system warning threshold states generated from the driving endurance index DEI [ ((t);

defining a threshold value for DEI (t) below WarningStatus [ DEI (t) ] based on t1 x time point, or for OCDT (t) exceeding WarningStatus [ OCDT (t) ] based on t2 x time point; at t1, a judgment result is obtained, and the judgment result is transmitted to the early warning module.

18. The vehicle networking data informatization-based vehicle user health and behavior monitoring method according to claim 17, wherein, in step 3-2 ", further, based on the predicted time point t3, DEI (t) exceeds the modified warning threshold state set of the WarningStatus [ HR (t) ] system; and obtaining a judgment result and transmitting the judgment result to the early warning module.

19. The method for monitoring health and behavior of a vehicle user based on internet-of-vehicles data informatization of claim 16, wherein step 3-2' further sets the behavior information AII of the measured object based on the change of the behavior information AII, and corrects DEI = DEI (t0) - (a2 = odt (t) 2 + a1 × odt (t) + a0) -f (AII), wherein f and a are fitting functions; if the behavior information AII is anteversion, f (AII) = f1(AII (t)); if the behavior information AII is retroverted, f (AII) = f2(AII (t)); if the behavior information AII is left-leaning, f (AII) = f3(AII (t)); if the behavior information AII is right dip, f (AII) = f4(AII (t)); other, f (aii) = f5(aii (t)); as time progresses, WarningStatus [ OCDT [ () ]) is a modified set of system warning threshold states generated from the driving endurance index DEI [ ((t);

20. The vehicle user health and behavior monitoring method based on vehicle networking data informatization according to claim 14 or 16, wherein the expression of the fitting function of the modified driving endurance index about the parameter X can be obtained based on historical data statistics of drivers, real world big data statistics, an integrated model of real world big data and personalized data, and one or more of the above data acquisition, and the fitting of the function comprises a polynomial function, an exponential function, a piecewise fitting, and a nonlinear fitting.

21. The vehicle user health and behavior monitoring method based on vehicle networking data informatization according to claim 14 or 16, characterized in that the coefficient of the fitting function of the modified driving endurance index with respect to the parameter X can be obtained based on the past historical data statistics of the driver, can be obtained based on the real world big data statistics, can be obtained based on an integrated model of the real world big data and personalized data, and can be obtained based on one or more of the aforementioned data acquisitions; the fitting of the function includes polynomial function, exponential function, piecewise fitting, nonlinear fitting.

22. The vehicle networking data informatization-based vehicle user health and behavior monitoring method according to claim 13, further comprising the steps of 5, judging and removing early warning; acquiring a physiological parameter, namely a mental Stress index MSI, and mapping the mental Stress index Stress (HRV (t))), HRV (t)) = HRV ((LF/HF) (t)); mapping the mental stress index value into 0-100 points, wherein the larger the numerical value is, the more pressure is felt, 0-20 means that the pressure is good, 20-40 means that the pressure is acceptable, 40-60 means that the pressure is slightly felt, 60-80 means that the pressure is medium, and 80-100 means that the pressure is severe; the recovery of the fused driving endurance index DEI as a function of the mental stress:

if 0 < MSI (t) ≦ 20, δ dei (t) = f1(MSI (t));

if 20 < MSI (t) ≦ 40, δ dei (t) = f2(MSI (t));

if 40 < MSI (t) ≦ 60, δ dei (t) = f3(MSI (t));

if 60 < MSI (t) ≦ 80, δ dei (t) = f4(MSI (t));

if 80 < MSI (t) ≦ 100, δ dei (t) = f5(MSI (t));

wherein t is a time point; f is a fitting function; δ DEI (t) is the driving endurance index loss, δ DEI (t) = DEI (t0) -DEI (t); dei (t) driving endurance index; DEI (t0) is the initial driving endurance index of the measured object;

and if MSI (t) is less than or equal to 40, removing the early warning.

23. The vehicle networking data informatization-based automobile user health and behavior monitoring method according to claim 13, wherein the early warning module in step 4 performs corresponding acousto-optic and vibration early warning according to the fatigue state and behavior result of the object to be detected, specifically:

if the behavior of the object to be detected is judged to be fatigue state and is judged to be severe fatigue and fatigue, the display module flickers to display the current fatigue state result, the vibration module works to enable the driver seat to generate vibration, and the voice module simultaneously plays prerecorded audio signals to jointly realize the early warning function;

aiming at two fatigue states of severe fatigue and fatigue, the working frequency of the vibration module is higher than the frequency corresponding to fatigue during severe fatigue.

Technical Field

The invention relates to the technical field of user health monitoring, in particular to an automobile user health and behavior monitoring system and method based on Internet of vehicles data informatization.

Background

With the rapid development of modern society and the rapid development of transportation industry, new energy automobiles are gradually popularized, the automatic driving technology is increasingly broken through, and the travel of traffic occupies more and more time. For a long time in the future, the transition still occurs in the stage of both automatic driving and man-made driving, so that the health condition, mental state and behavior condition of the driver during driving are still important factors influencing traffic safety. In particular, fatigue driving behavior of the driver is a potential risk of inducing traffic accidents. The health condition, mental state and behavior of passengers also need to pay more attention, such as event monitoring when infants leave behind home cars or school bus students leave behind cars, interactive driving by long-distance drivers or health condition monitoring when passengers stay in cars at night.

The prior literature patent proposes a plurality of different monitoring technologies for the health condition, mental state and behavior condition of a driver or a passenger, but the two monitoring technologies are separated into two parts, and a unified technical solution is not integrated. If the technical scheme of the camera is applied, privacy can be invaded, and the facial mental state and simple behavior conditions are mainly concerned, so that the privacy is greatly restricted by light and environmental factors; and if applied physiological signals such as an electroencephalogram helmet, a pulse wave bracelet watch, an electrocardio steering wheel electrode and the like, the monitoring object needs to contact or wear a sensor, so that the burden and the inconvenience are caused. Furthermore, the schemes all want to detect the fatigue state in real time, the landing difficulty of the applications in the real world is very large, and even if the detection is accurate, accidents are likely to happen within the minutes and seconds of the occurrence of the fatigue driving event, so that the early warning and prevention are concerned more. At the same time, these solutions are essentially monitoring and do not provide a good means to help restore mental state.

Disclosure of Invention

The invention provides an automobile user health and behavior monitoring system and method based on internet of vehicles data informatization, which simultaneously pay attention to health conditions, mental states and behavior conditions of drivers and passengers, are integrated and unified in technical path, are convenient to realize and greatly improve the safety of automobile driving and riding. Especially, early warning is emphasized in driving fatigue monitoring, and a driver is helped to pay attention to unnecessary fatigue driving risks in advance to avoid the risks.

In order to achieve the purpose, the invention provides the following technical scheme: a system and a method for monitoring the health and behavior of automobile users based on Internet of vehicles data informatization comprise an information acquisition module, a transmission module, a control processing module and an early warning module which are connected in sequence;

the transmission module is used for transmitting the signal source information acquired by the information acquisition module to the control processing module;

And the early warning module is used for carrying out sound, light and/or vibration early warning according to the judgment result of the control processing module.

As a further improvement of the above technology, the preset driving endurance index may be obtained based on a sleep data state set obtained before the subject drives, a recovery data state set obtained during a short-term rest or relaxation training process of the subject, a historical data statistical state set obtained by the subject in the past, a real world big data statistical state set obtained, an integrated model state set obtained by the real world big data and personalized data, or one or more of the above-mentioned obtaining.

As a further improvement of the technology, the preset driving endurance index is configured for the tested object in a self-defined mode.

As a further improvement of the above technique, the information acquisition module includes a non-contact acquisition module;

the non-contact acquisition module is used for acquiring the physiological parameters and/or behavior information of the tested object to obtain the driving endurance index of the tested object.

As a further improvement of the above technology, the non-contact acquisition module is a vibration sensor which is arranged in a non-contact manner with the object to be measured in a force-bearing area below the buttocks and/or a force-bearing area behind the buttocks, the vibration sensor is used for acquiring behavior information of the object to be measured and transmitting the behavior information to the control processing module, the behavior information includes driving duration of the object to be measured and a posture information index, and the posture information index of the object to be measured is generated from one or more of a sitting posture state, an abnormal sitting posture value and an abnormal sitting posture state duration value.

As a further improvement of the above technique, the control processing module includes: the model generation module is used for judging the driving endurance state of the tested object according to the received signal source information and generating a personalized driving endurance index model of the tested object, and the personalized driving endurance index model is configured to generate a corrected system early warning threshold state set for the transition from the waking state to the fatigue state of the tested object; the data processing module is used for receiving the behavior information, carrying out primary processing on the behavior information and calculating the driving endurance index of the tested object according to the processed behavior information; wherein the preliminary processing comprises filtering, amplifying and A/D conversion; and the data comparison module is used for updating and correcting the driving endurance index according to the received signal source information, synchronously generating a corrected system early warning threshold state set, judging the fatigue state of the tested object and obtaining a judgment result.

As a further improvement of the above technique, the transmission module includes: and the Bluetooth module is used for receiving the judgment result obtained by the control processing module and transmitting the judgment result to the early warning module.

As a further improvement of the above technology, the early warning module includes: the display module is used for displaying a visual alarm interface of the driving endurance state and behavior of the object to be tested; the vibration module is used for realizing vibration of the driver seat; and the voice module is used for playing the prerecorded audio signal.

As a further improvement of the technology, the vibration module comprises a voltage stabilizing drive circuit and a vibration motor which are sequentially connected, and can realize vibration with different frequencies.

As a further improvement of the above technique, the vibration sensor is a sensor that equivalently converts physical quantities based on acceleration, pressure, velocity, and displacement, and includes an optical fiber sensor.

As a further improvement of the above technique, the vibration sensor further includes: the physiological acquisition module is used for acquiring physiological parameters of a to-be-detected object; the physiological parameters include heart rate, heart rate variability, breathing rate, breathing pattern, stress index, fatigue index.

As a further improvement of the above technique, the physiological acquisition module is a bracelet-worn device comprising:

A vehicle user health and behavior monitoring method based on vehicle networking data informatization comprises the following steps:

step 2, transmitting the signal source information acquired in the step 1 to a control processing module through a transmission module;

step 3, the control processing module judges the fatigue state of the object to be detected according to the signal source information;

As a further improvement of the above technology, step 3, the control processing module judges the fatigue state of the object to be measured according to the signal source information, specifically: step 3-1, generating a preset system early warning threshold state set based on a preset driving endurance index DEI (t0), wherein the preset system early warning threshold state set comprises: starting early warning state information WarningStatus [ X (T0) ] = WarningStatus [ [ X1(T0), X2(T0), X3(T0), …, xn (T0) ] T ] with respect to a parameter X = [ X1, X2, X3, …, xn ] T; (ii) an early warning state curve, warnengstatus [ DEI (t) ], about DEI changes over time; step 3-2, monitoring the parameter X = [ X1, X2, X3, …, xn ] T during driving, and obtaining a modified driving endurance index DEI [ (X, T) = DEI [ ] about the parameter X changing along with time (X1, X2, X3, …, xn ] T, T); step 3-3, updating warning threshold state information WarningStatus [ X (T) ] = WarningStatus [ X1(T), X2(T), X3(T), …, xn (T) ] T ] regarding the parameter X = [ X1, X2, X3, …, xn ] T based on the corrected driving endurance index DEI [ (X, T) ]; and 3-4, the updated system early warning threshold state set comprises two parts: WarningStatus [ [ x1(T), x2(T), x3(T), …, xn (T) ] T ]. U.WarningStatus [ DEI (T) ]; step 3-5, judging an early warning time point T1 according to DEI (X, T) and WarningStatus (DEI (T)); step 3-6, judging an early warning time point T2[ X ] = [ T2(X1), T2(X2), T2(X3), … and T2(xn) ] according to X (T) and WarnngStatus [ X (T); and 3-7, starting early warning at the earliest occurrence of any early warning time point according to the early warning time points of T1 and T2.

As a further improvement of the above technology, the control processing module determines the fatigue state of the object to be detected according to signal source information, where the signal source information includes a parameter X, and X is one or more of driving time, sitting posture state, heart rate variability, respiratory rate, respiratory pattern, mental stress index, and fatigue index.

As a further improvement of the above technology, step 3, the control processing module judges the fatigue state of the object to be measured according to the signal source information, specifically: step 3-1, generating a preset system early warning threshold state set by a preset driving endurance index: setting a preset value of a current driving endurance index of a tested object in a self-defined configuration as DEI (t0), automatically generating a preset system early warning threshold state set WarningStatus (t0) matched with the preset value according to the preset value, and defining driving endurance index loss delta DEI based on single continuous driving time OCDT (t0) -delta DEI (t), delta DEI (t) = g (ODT (t)); as the duration of a single continuous driving increases, the corresponding system early warning threshold state sets warnengstatus (DEI, OCDT), DEI (t) = DEI (t0) - (a2 ^ odt (t) ^2 + a1 ^ odt (t) + a0), δ DEI (t) = g (odt (t) = a2 ^ odt (t) ^2 + a1 ^ odt (t) + a 0); in the formula, WarningStatus [ DEI ] is a system early warning threshold state of a driving endurance index, and WarningStatus [ ODT ] is a system early warning threshold state set of single continuous driving time;

WarningStatus (DEI, OCDT) is a system early warning threshold state set generated according to a driving endurance index DEI (t 0);

As a further improvement of the above technique, step 3-2', further, based on the variation of the heart rate HR, setting the physiological parameter HR of the subject, and obtaining a modified DEI = DEI (t0) - (a2 = odt (t) ^2 + a1 ^ odt (t) + a0) -f (HR), where f and a are fitting functions;

as time progresses, WarningStatus [ OCDT [ () ]) is a modified set of system warning threshold states generated from the driving endurance index DEI [ ((t);

As a further improvement of the above technique, step 3-2 ″, further, based on the predicted time point t3, DEI · (t) exceeds the corrected warning threshold state set of the warnengstatus [ HR · (t) ] system; and obtaining a judgment result and transmitting the judgment result to the early warning module.

As a further improvement of the above technique, step 3-2', further, based on the change of the behavior information AII, setting the behavior information AII of the object to be measured, and correcting DEI = DEI (t0) - (a2 = DEI (t) ^2 + a1 ^ odt (t) + a0) -f (AII), wherein f and a are fitting functions; if the behavior information AII is anteversion, f (AII) = f1(AII (t)); if the behavior information AII is retroverted, f (AII) = f2(AII (t)); if the behavior information AII is left-leaning, f (AII) = f3(AII (t)); if the behavior information AII is right dip, f (AII) = f4(AII (t)); other, f (aii) = f5(aii (t)); as time progresses, WarningStatus [ OCDT [ () ]) is a modified set of system warning threshold states generated from the driving endurance index DEI [ ((t);

As a further improvement of the technology, the expression of the fitting function of the modified driving endurance index about the parameter X can be obtained based on the statistics of past historical data of the driver, the statistics of real world big data, the integrated model of the real world big data and personalized data and one or more of the data acquisition, and the fitting of the function comprises a polynomial function, an exponential function, a piecewise fitting and a nonlinear fitting.

As a further improvement of the above technique, the coefficient of the fitting function that corrects the driving endurance index with respect to the parameter X may be obtained based on statistics of past historical data of the driver, may be obtained based on statistics of real world big data, may be obtained based on an integrated model of real world big data and individualized data, and may be obtained based on one or more of the foregoing data acquisitions; the fitting of the function includes polynomial function, exponential function, piecewise fitting, nonlinear fitting.

As a further improvement of the technology, the method also comprises the step 5 of judging and removing the early warning; acquiring a physiological parameter, namely a mental Stress index MSI, and mapping the mental Stress index Stress (HRV (t))), HRV (t)) = HRV ((LF/HF) (t)); mapping the mental stress index value into 0-100 points, wherein the larger the numerical value is, the more pressure is felt, 0-20 means that the pressure is good, 20-40 means that the pressure is acceptable, 40-60 means that the pressure is slightly felt, 60-80 means that the pressure is medium, and 80-100 means that the pressure is severe; the recovery of the fused driving endurance index DEI as a function of the mental stress:

if 0 < MSI (t) ≦ 20, δ dei (t) = f1(MSI (t));

if 20 < MSI (t) ≦ 40, δ dei (t) = f2(MSI (t));

if 40 < MSI (t) ≦ 60, δ dei (t) = f3(MSI (t));

if 60 < MSI (t) ≦ 80, δ dei (t) = f4(MSI (t));

if 80 < MSI (t) ≦ 100, δ dei (t) = f5(MSI (t));

and if MSI (t) is less than or equal to 40, removing the early warning.

As a further improvement of the above technology, step 4, the early warning module performs corresponding acousto-optic and vibration early warning according to the fatigue state and behavior result of the object to be detected, specifically:

aiming at two fatigue states of severe fatigue and fatigue, the working frequency of the vibration module is higher than the frequency corresponding to fatigue during severe fatigue.

Through implementing above technical scheme, have following technological effect: the early warning is emphasized in advance in driving fatigue monitoring, and a driver is helped to pay attention to unnecessary fatigue driving risks in advance to avoid the risks.

Drawings

FIG. 1 is a schematic illustration of the component deployment of the present invention;

FIG. 2 is a schematic view of the variation of the parameters of the driving process of the present invention over time;

FIG. 3 is a schematic view of the variation of the parameters of the driving process of the present invention over time;

FIG. 4 is a graphical illustration of the variation of the parameters of the driving process of the present invention over time;

FIG. 5 is a graphical illustration of the variation of the parameters of the driving process of the present invention over time;

FIG. 6 is a schematic view of the present invention for a parking space;

FIG. 7 is a schematic view of the present invention for a vehicle parking space;

FIG. 8 is a schematic diagram of the variation of parameters of the relaxation training process of the present invention over time;

FIG. 9 is a schematic diagram of the time-dependent parameter change of the sleep recovery process of the present invention;

fig. 10 is a block diagram of the system of the present invention.

A. A driving position; B. a passenger location; (a 1, a2, B1, B2), a vibration sensor; C. a vehicle-mounted navigation terminal; (D1, D2), and a sound.

Detailed Description

In order to better understand the technical scheme of the invention, the following detailed description is made on the embodiments provided by the invention in combination with the accompanying drawings.

As shown in fig. 10, the system for monitoring health and behavior of the vehicle user based on the data informatization of the internet of vehicles according to the embodiment of the application includes an information acquisition module, a transmission module, a control processing module and an early warning module, which are sequentially connected;

the transmission module is used for transmitting the signal source information acquired by the information acquisition module to the control processing module;

And the early warning module is used for carrying out sound, light and/or vibration early warning according to the judgment result of the control processing module.

The preset driving endurance index can be obtained based on a sleep data state set of the tested object before driving, a recovery data state set of the tested object in a short-time rest or relaxation training process, a historical data statistical state set of the tested object in the past, a real world big data statistical state set, and an integrated model state set of real world big data and personalized data, or one or more of the above-mentioned obtaining.

And the preset driving endurance index is configured for the tested object in a user-defined mode.

The information acquisition module comprises a non-contact acquisition module; the non-contact acquisition module is used for acquiring the physiological parameters and/or behavior information of the tested object to obtain the driving endurance index of the tested object.

The non-contact acquisition module is a vibration sensor which is arranged in a stress area below the hip and/or a back stress area of the tested object in a non-contact mode, the vibration sensor is used for acquiring behavior information of the tested object and transmitting the behavior information to the control processing module, the behavior information comprises driving time and a posture information index of the tested object, and the posture information index of the tested object is generated by one or more of a sitting posture state, a sitting posture abnormal value and a sitting posture abnormal state duration value.

The control processing module comprises: the model generation module is used for judging the driving endurance state of the tested object according to the received signal source information and generating a personalized driving endurance index model of the tested object, and the personalized driving endurance index model is configured to generate a corrected system early warning threshold state set for the transition from the waking state to the fatigue state of the tested object;

The transmission module includes: and the Bluetooth module is used for receiving the judgment result obtained by the control processing module and transmitting the judgment result to the early warning module.

The early warning module includes: the display module is used for displaying a visual alarm interface of the driving endurance state and behavior of the object to be tested; the vibration module is used for realizing vibration of the driver seat; and the voice module is used for playing the prerecorded audio signal.

The vibration module comprises a voltage stabilization driving circuit and a vibration motor which are sequentially connected, and can realize vibration with different frequencies.

The vibration sensor is a sensor which equivalently converts physical quantities on the basis of acceleration, pressure, speed and displacement, and comprises an optical fiber sensor.

The vibration sensor further includes: the physiological acquisition module is used for acquiring physiological parameters of a to-be-detected object; the physiological parameters include heart rate, heart rate variability, breathing rate, breathing pattern, stress index, fatigue index.

The physiology acquisition module is bracelet formula device of wearing, includes:

Example 1: monitoring of driving position physiological parameters and behaviors and application of monitoring of fatigue driving

When a driver is in the driving seat A, a vibration sensor can be deployed to monitor physiological parameters and behaviors. The raw signal acquisition of the vibration sensor can be carried out by an acceleration sensor, a pressure sensor, a speed sensor, a displacement sensor and the like, or a sensor (such as an electrostatic charge sensitive sensor, an inflatable micro-motion sensor, an optical fiber sensor and the like) which equivalently converts physical quantity on the basis of acceleration, pressure, speed and displacement. When the original signals are measured and collected, the vibration sensor can be generally placed in a stress area at the back of a lying and supine human body, a stress area at the back of a supine human body with a certain inclination angle, a stress area at the back of a lying human body of a wheelchair or other objects capable of leaning against, a stress area at the upper part of a seat and the lower part of the hip of a semi-lying human body and the like for collection and measurement. As shown in FIG. 1, A is a driving seat, and at the moment, a vibration sensor can be deployed in a force-bearing area A1 below the buttocks of a driver or a force-bearing area A2 behind the buttocks of the driver, so that data can be acquired in a non-contact and non-sensing manner.

Based on the collected original signals of the vibration sensor, parameters such as respiratory frequency, respiratory mode and the like can be extracted, and heart impact waveform analysis and calculation of heart rate and heart rate variability time-frequency parameters can be extracted, so that real-time calculation can be realized, and the parameters can be used for subsequent display, storage, recording or transmission; based on one or more of the parameters, different combinations are carried out, mental stress index evaluation models and fatigue index evaluation models suitable for different scenes can be further constructed, and real-time calculation can be carried out for subsequent display, storage, recording or transmission; meanwhile, the in-place state of a driver can be monitored, the continuous driving time can be analyzed, multiple sensors can be added to monitor different sitting posture states such as forward leaning, backward leaning, left leaning and right leaning states, and real-time calculation can be carried out for subsequent display, storage, recording or transmission. The driver can preview the relevant data on the vehicle-mounted navigation terminal C, and can also preview the relevant data in a mobile phone mode, a tablet personal computer mode, a webpage end mode and the like.

And based on a preset system early warning threshold state set, giving a system early warning when one or more of the parameters exceeds a certain limit value, wherein the preset system early warning threshold state set is generated based on a preset driver driving endurance index. The preset driving endurance index represents an index for objectively evaluating the sustainable driving ability of the driver, and can be acquired based on a sleep data state set before the driver drives, a recovery data state set during short-term rest or relaxation training of the driver, a historical data statistical state set of past drivers, a real world big data statistical state set, an integrated model state set of real world big data and personalized data, and one or more of the data acquisition. Of course, the driver can also manually configure the driving endurance index value according to self subjective feeling customization. Of course, when the driving endurance index exceeds a certain limit value, a system early warning is given.

In the present invention, for the purpose of unified description, Driving endurance index dei (Driving endurance index), heart Rate hr (heart Rate), heart Rate variability hrv (heart Rate variability), respiratory Rate rr (respiratory Rate), respiratory mode rm (respiratory mode), mental Stress index msi (mental Stress index), fatigue index fi (fatigue index), single continuous Driving time ocdt (one continuous Driving time), cumulative Driving time cdt (cumulative Driving time), and posture Information index aii (posture Information index) are not defined.

In this embodiment, the preset driving endurance index is configured manually by the owner before getting on the vehicle (the user-defined setting value has a safety margin and cannot exceed a reasonable range). Assuming that a driver customizes and configures the current driving endurance index to be DEI (t0), according to the preset value, a system early warning threshold state set WarningStatus (t0) matched with the DEI is automatically generated, wherein the WarningStatus comprises one or more of single duration driving time, accumulated driving time, heart rate abnormal value, heart rate abnormal duration, respiratory rate abnormal value duration, heart rate variability time-frequency parameter abnormal value duration, respiratory pattern abnormal value duration, mental stress index abnormal value duration, fatigue index abnormal value duration, various sitting posture abnormal value, various sitting posture abnormal state duration and the like. In one embodiment, the driving endurance index can be expressed as a score of 0-100, a gear of 1-5 and the like, as long as the sustainable driving ability of different scores or intervals can be expressed in a distinguishing manner, various representation modes can be adopted, and then a preset system early warning threshold state set is generated according to the driving endurance index and is used as an early warning judgment condition for insufficient continuous driving ability of a driver.

The driving endurance index represents the ability of a driver to drive continuously, and the driving ability is continuously lost during the driving process of the driver, namely the driving endurance index is lost. And generating a driving endurance index curve of the driving endurance index changing along with time according to the monitored physiological parameters and behavior information of the driver and the preset initial driving endurance index DEI (t 0).

To illustrate in the simplest example, assuming that only a driving endurance index model related to a single duration of driving time is established, driving endurance index loss δ DEI is defined, DEI (t) = DEI (t0) - δ DEI (t), δ DEI (t) = g (odt)), that is, driving endurance index loss is related to a single duration of driving time. It may be fitted using a function such as a polynomial function, exponential function, piecewise fit, non-linear fit, etc. The expressions and coefficients of the fitting function may be obtained based on statistics of historical driver past data, may be obtained based on statistics of real world big data, may be obtained based on an integrated model of real world big data and individualized data, and may be obtained based on one or more of the foregoing data acquisitions. The data referred to later in the present invention can be acquired by these data sets.

Taking a quadratic function as an example, without defining the simplest linear function, δ DEI (t) = g (odt) (t) = a2 ^ odt (t) ^2 + a1 ^ odt (t) + a0, then DEI (t) = DEI (t0) - (a2 ^ odt (t) ^2 + a1 ^ odt (t) + a0) with increasing single sustained driving time. As shown in FIG. 2, a DEI curve and an OCDT curve are plotted over time. The solid line is the DEI curve, and as time goes on, the driving endurance index is continuously decreased after being lost; the long dashed line is the OCDT curve, which generally rises continuously over time, and this embodiment is given a reverse plot for clarity of the illustration. The corresponding set of system warning threshold states WarningStatus (DEI, OCDT) includes two aspects, namely, the system warning threshold state WarningStatus [ DEI ] of the driving endurance index and the system warning threshold state WarningStatus [ ODT ] of the single duration driving time. When the true DEI is found (t) to be below the warnengstatus [ DEI ] defined threshold, as shown in fig. 2 at the time point t 1; or ODT (t) exceeds the warnengstatus ODT limit threshold, as shown at time t2 in fig. 2; combining the two states, the system gives an early warning, i.e. at time t1, the system is already able to give an early warning.

At this time, the warnengstatus (DEI, OCDT) is a state set generated from the initial DEI (t0) at the beginning, and is maintained as it is thereafter. Further, considering that the parameter changes of the OCDT along with the DEI, the corresponding system early warning threshold state set WarningStatus (t) becomes a variable state set. As shown in fig. 3, the originally constant WarningStatus [ DEI ] becomes a curve of WarningStatus [ DEI ] that gradually rises with the duration of a single driving, and the originally constant WarningStatus [ ODT ] becomes a curve of WarningStatus [ ODT ] that gradually changes with the decreasing driving endurance index. When the true dei (t) is found to be below the warnengstatus [ dei (t) ] defined threshold, the time point t1 as shown in fig. 3; or odt (t) exceeds a warnengstatus odt (t) defined threshold, as shown at time t2 in fig. 3; by combining the two states, the system gives an early warning, i.e. at time t1, the system is already able to give an early warning. At this time, the obtained time point t1 is earlier than the time point t1, the time point t2 is earlier than the time point t2, and the system can acquire the early warning state earlier and give a warning signal to the driver in advance.

Further, introducing the influence of the heart rate HR, generally, the higher the heart rate is, the more the driver expends energy on the driving behavior, and thus the greater the loss of the driving endurance index will be. As shown in fig. 4, the upper half curve is a parameter variation diagram corresponding to the previous embodiment, and the lower half curve is a heart rate trend diagram. At this time, looking at the upper half of the curve, depending on the continuous monitoring of the heart rate by the vibration sensor, based on the previous embodiment, DEI = DEI (t0) - (a2 ^ odt (t) ^2 + a1 ^ odt (t) + a0) -f (HR) is corrected, where f (HR) is a function with respect to HR, and likewise it may be fitted with a function, such as a polynomial function, an exponential function, a piecewise fit, a nonlinear fit, etc., and the expression and coefficients of the fitted function may be obtained based on various data (source) statistical methods.

As a result, the modified driving endurance index curve DEI (t) tends to be located below the original DEI (t) curve in the general trend as time progresses. Then, based on the corrected DEI (t), a warnengstatus [ OCDT (t) ] curve can be obtained, and since DEI (t) is generally smaller than DEI (t), WarningStatus [ OCDT (t) ] changes faster than the original state, the general trend thereof is located above the WarningStatus [ OCDT (t) ] curve. When the true DEI (t) is found to be below the warnengstatus [ DEI (t) ] defined threshold, time t1 is shown in fig. 4, which is earlier than time t 1; when the true OCDT (t) is found to exceed the warnengstatus [ OCDT (t) ] threshold, time t2 is shown in fig. 4, which is earlier than time t 2. Therefore, according to the comprehensive judgment of t1 and t2, the system can acquire the early warning state earlier and give warning signals to the driver in advance. Referring to the lower half curve, assuming that the dot-dash line is a heart rate early warning line and the solid line is a heart rate trend curve tracked in real time, at time t3, it is found that the heart rate value exceeds the heart rate early warning line warnengstatus [ HR (t) ] corrected based on DEI (t), and at this time, an early warning can be performed. And comprehensively comparing t3 with t1| | t2 |, and performing early warning at the early time point. In this embodiment, t3 is just earlier than t1| | t2 |, so the warning state can be turned on at time t 3. In one embodiment, the heart rate early warning time point can be judged in various ways such as finding that the heart rate exceeds the early warning line for the nth (N > 1) time, or the heart rate exceeds the duration of the early warning line, or delaying for a set time length after the heart rate exceeds the early warning line. In one embodiment, different heart rate warning mechanisms may produce t3 later than t1 t2, or even later than t1 t 2; however, the time point t1 × t2 is not necessarily later than the time point t1 × t2, and the time point t1 × t2 is not necessarily later than the time point t1 × t 2.

Through the description of the foregoing embodiment, from the time point t1| | t2 at which the fatigue state of the driver is finally detected in the conventional art, the warning time is advanced to the state t1| | t2 by adding the correction of the single continuous driving time; and then adding the heart rate correction, and advancing the early warning time to t1 t2 t3 to further obtain a more prospective early warning state.

In one embodiment, more driving behavior parameters can be considered, the vibration sensor can easily obtain sitting posture parameters of the driver, analyze sitting posture information of the driver such as forward inclination, backward inclination, left inclination and right inclination, and can analyze the inclination strength (such as slight left inclination, moderate left inclination and large left inclination), the switching frequency, the switching type (such as forward inclination to left inclination, right inclination to left inclination and backward inclination to left inclination) and the like. Each driver has a comfortable sitting position adapted thereto, which may result in a loss of driving endurance index faster than in a normal comfortable sitting position when influenced by road conditions, environmental conditions, etc., such as frequent jerks, bumps, etc. Of course, failure to maintain the same sitting position for too long a period of time, such as an over-long stretch of road, a single line of sight, etc., may cause a single loss of attention, poor blood circulation, etc., which may also result in a loss of driving endurance index faster than its normal comfortable sitting position. To simplify the application of the embodiment, the effect of the previous HR is replaced by the effect of the sitting position AII. As shown in fig. 5, the upper half curve is a schematic diagram of parameter variation corresponding to the previous embodiment, and the lower half curve is a schematic diagram of sitting posture trend. At this time, depending on the continuous monitoring of the sitting posture by the vibration sensor, the upper half of the curve is corrected based on the previous embodiment by DEI = DEI (t0) - (a2 × (odt) (t) ^2 + a1 × (t) + a0) -f (AII), where f (AII) is a function with respect to AII, and similarly it may be fitted with a function such as a polynomial function, an exponential function, a piecewise fitting, a nonlinear fitting, etc., and the expression and coefficient of the fitting function may be obtained based on various data (source) statistical methods. It is not established as a piecewise fitting function:

if anteversion, f (aii) = f1(aii (t));

upon retroversion, f (aii) = f2(aii (t));

if left leaning, f (aii) = f3(aii (t));

if right dip, f (aii) = f4(aii (t));

if normal, f (aii) = f5(aii (t));

each piecewise function may also be fitted to the actual data (source) using methods such as polynomial functions, exponential functions, piecewise fitting, nonlinear fitting, and the like. As a result, the modified driving endurance index curve DEI (t) tends to be located below the original DEI (t) curve in the general trend as time progresses. Then, based on the corrected DEI (t), a warnengstatus [ OCDT (t) ] curve can be obtained, and since DEI (t) is generally smaller than DEI (t), WarningStatus [ OCDT (t) ] changes faster than the original state, the general trend thereof is located above the WarningStatus [ OCDT (t) ] curve. When the true DEI (t) is found to be below the warnengstatus [ DEI (t) ] defined threshold, time t1 is shown in fig. 5, which is earlier than time t 1; when the true OCDT (t) is found to exceed the warnengstatus [ OCDT (t) ] threshold, time t2 is shown in fig. 5, which is earlier than time t 2. Therefore, according to the comprehensive judgment of t1 and t2, the system can acquire the early warning state earlier and give warning signals to the driver in advance.

Through the description of the foregoing embodiment, from the time point t1| | t2 at which the fatigue state of the driver is finally detected in the conventional art, the warning time is advanced to the state t1| | t2 by adding the correction of the single continuous driving time; and then, after the sitting posture correction is added, the early warning time is advanced to t1| | t2 |, and a more prospective early warning state is further obtained.

Of course, in one embodiment, the aforementioned heart rate HR and sitting posture AII may also be added simultaneously. Furthermore, more physiological parameters and behavior parameters can be added to correct the driving endurance index curve, including one or more of single duration driving time, accumulated driving time, heart rate variability time-frequency parameters, respiratory rate, respiratory pattern, sitting posture state, abnormal heart rate values, abnormal heart rate duration, abnormal respiratory rate values, abnormal heart rate variability time-frequency parameters, abnormal respiratory pattern values, abnormal mental stress index values, abnormal fatigue index values, abnormal sitting posture state durations and the like. The adding steps are as follows:

1. based on the preset driving endurance index DEI (t0), generating a preset system early warning threshold state set comprising: starting early warning state information WarningStatus [ X (T0) ] = WarningStatus [ [ X1(T0), X2(T0), X3(T0), …, xn (T0) ] T ] about a parameter X = [ X1, X2, X3, …, xn ] T (X may be one or more of the aforementioned physiological or behavioral parameters); (ii) an early warning state curve, warnengstatus [ DEI (t) ], about DEI changes over time;

2. monitoring a parameter X = [ X1, X2, X3, …, xn ] T during driving, and obtaining a modified driving endurance index DEI [ (X, T) = DEI [ ] ([ X1, X2, X3, …, xn ] T, T) of the DEI with respect to the parameter X over time;

3. updating warning threshold state information WarningStatus [ X (T) ] = WarningStatus [ X1(T), X2(T), X3(T), …, xn (T) ] T ] regarding a parameter X = [ X1, X2, X3, …, xn ] T, based on the corrected driving endurance index DEI [ ((X, T));

4. the updated system early warning threshold state set comprises two parts: WarningStatus [ [ x1(T), x2(T), x3(T), …, xn (T) ] T ]. U.WarningStatus [ DEI (T) ];

5. judging an early warning time point T1 according to DEI (X, T) and WarningStatus (DEI (T));

6. judging an early warning time point T2[ X ] = [ T2(X1), T2(X2), T2(X3), …, T2(xn) ] according to X (T) and WarnngStatus [ X (T);

7. according to the early warning time points of T1 and T2, the early warning is started when any early warning time point occurs at the earliest.

When the early warning event is detected, the early warning prompt is given in the vehicle, the sound alarm wakes up the vehicle owner to prompt the vehicle owner to search for a safe parking area such as a high-speed service area as soon as possible to have a safe parking rest. In one embodiment, the warning can be performed by various ways such as turning on other warning devices on the vehicle, including sound, light, vibration, and the like, for example, double flashing of the lights to warn the attention of the surrounding vehicle, the sound in the vehicle D1 and D2 giving warning music to wake up the driver to concentrate, and the vibration sense of the back or the hip to wake up the driver to concentrate.

The driver can process the early warning after receiving the early warning, the current early warning reliable state can be marked, the system can record the marking accuracy, continuously self-learn and correct the preset threshold state set, continuously iterate and optimize the real data model matching the physiological parameters and behaviors of the driver, and correct the early warning accuracy. In one embodiment, the system can be integrated with vehicle-mounted navigation, when the driver receives early warning and gives a recommended parking rest position, the driver can directly take a rest in a related safe parking area according to the recommended navigation.

Example 2: passenger position physiological parameters and behavior monitoring, and safety monitoring application

When the vibration sensor is deployed in the passenger seat, the physiological parameters and behavior data of the passenger seat can be monitored. As shown in fig. 1, B is a passenger space (there may be other passenger spaces in the vehicle, only for illustration), and at this time, a vibration sensor may be disposed in a force-receiving area B1 below the hip of the passenger or a force-receiving area B2 behind the hip of the passenger, and the data can be collected in a non-contact and non-sensitive manner.

1) Physiological parameters of passengers such as heart rate and respiratory rate parameters are monitored, and prompts are given when abnormity occurs or relevant data is recorded so as to help the passengers to find problems early. The preset abnormal value can be a self-defined state set, a normal state set obtained by analyzing a past data set of a passenger (when the passenger is in an exclusive parking space), a statistical result state set of massive real world data, and a state set obtained by integrating the large data into personalized data.

2) Monitoring the in-place state of passengers, if students may be missed to get on the school bus at some start-stop positions, pre-set travel in-place number of people can be marked in advance, and when the students may be missed to get on the school bus at the start-stop positions (such as the students in the service area go out again after going to the washroom), an early warning is given to indicate that the passengers are not in place. Or the number of people in place when going out is preset by the private car, and when the follow-up starting and stopping state changes, early warning is given when the passengers leave the private car, so that the passengers are not in place. At this time, the vibration sensor may need to be deployed in the whole car for monitoring the in-place state, fig. 6 is a schematic diagram of a certain five-seat car, four passenger seats B are provided outside the driving seat a, and it is assumed that the vibration sensor is deployed in all the passenger seats (1 driving seat and 4 passenger seats). When traveling for the whole family, the number of family members (no assumption is that 5 persons are used) can be preset in the system, the vehicle-mounted navigation terminal C can display in-place state maps of all positions, and when the number of bits monitored by the system is less than 5, an early warning prompt is given to indicate that the family members are not in place completely and the missing of getting on the bus is caused if a driver directly starts carelessly after the journey stops in a service area. The driver can respond to the relevant treatment measures immediately.

3) Monitoring the in-place state of passengers, such as the situation that family infants and children forget to enter a car, and the car windows are automatically closed to cause a suffocation death event, triggering corresponding early warning, such as car locking early warning prompt, when the corresponding seats are monitored to have the passengers, if a driver still locks the car, triggering physiological parameter abnormal prompt push in follow-up according to certain rules, such as timing push, triggering prompt push through excessive physical movement or sitting up and down, and the like, and reminding a car owner of possibly needing to return to the car to determine the state of the passengers. Further, can be when monitoring physiological parameter is unusual, can open certain door window space automatically to the authorized car, satisfy the circulation of air to protect the interior passenger safety of forgetting of car better. Or the vehicle sends out a warning or distress signal, and if people around the vehicle can see whether passengers are trapped in the vehicle or not, the passengers can be rescued. Similarly, as illustrated in fig. 6, when the vital signs (or the corresponding off-seat signal) are still monitored at the passenger seat before the owner turns off and locks the car, an early warning is given to indicate that there are passengers in the car. If the owner knows the information and still leaves, early warning information is pushed according to a certain rule in the follow-up process, and the owner is reminded of possibly needing to return to the interior of the vehicle to determine the state of the passenger. Further, if the physiological parameters of passengers in the vehicle are monitored to be abnormal, certain window gaps can be automatically opened for the authorized vehicle, air circulation is met, and safety of the passengers left in the vehicle is better protected. Or the vehicle sends out a warning or distress signal, and if people around the vehicle can see whether passengers are trapped in the vehicle or not, the passengers can be rescued.

4) The in-place state of the passengers is monitored, if the number of passengers is 1 in advance for an automatic driving automobile, when 2 or more passengers are monitored (sudden hijacking is possible), the passengers can be pushed to confirm, if the passengers are not confirmed in time, the authorized emergency contacts can be early-warned, the capacity of dealing with emergency events is enhanced, and the trip safety of the passengers is ensured. Similarly, as illustrated in fig. 6, if the number of persons getting on the train is 1, but the number of persons getting on the train exceeds the number of persons getting on the train, the person getting on the train is first sent to confirm the information, and if the person getting on the train cannot confirm the information in time, a security event may occur. Furthermore, the authorized emergency contact can be early-warned and pushed, the emergency contact can timely contact the order person to confirm the state, or other effective measures are taken, so that the capability of dealing with the emergency is enhanced, and the trip safety of the order person is ensured.

Example 3: relaxation training physiological parameter monitoring feedback

After the driver receives the fatigue early warning, the traditional technical scheme does not pay attention to how the follow-up driver recovers the mental state after the early warning is completed. Generally, after the early warning processing is performed, a driver needs to be prompted to go to a safe parking area for parking and rest. The system can also integrate a safe parking area recommended by a navigation system to directly guide the driver to go to the area for rest.

When a driver executes a parking rest operation, the traditional technical scheme has no relation with attention and no intervention, and can only depend on the driver to close eyes and nourish spirit for rest. In the embodiment, after the vibration sensor is deployed, the relaxation training module can be integrated to help the driver to improve the recovery efficiency more quickly, and meanwhile, feedback evaluation is made on the recovery condition of the driver, and the subsequent sustainable driving capability of the driver, namely the driving endurance index of the driver, is objectively evaluated. The driver can make more effective evaluation on the possibility of whether the driver can go out again according to subjective feeling and objective data of the driver, and the possibility of early warning of fatigue safety events is helped.

As shown in fig. 7, the car navigation terminal C is not taken as a carrier for example, a relaxation training application is installed in the terminal, and various relaxation training modules are built in the terminal, such as voice guidance for guiding or assisting the driver to relax, music therapy, VR therapy, binaural beat therapy, and the like. Assuming that voice guidance is taken as an example, the car audio shown in fig. 7 plays corresponding guidance audio, and the driver does not need to perform any extra operation, and only sits on the seat with close eyes, and relaxes the body and mind as much as possible in an immersive manner according to the guidance prompt voice. Of course, in one embodiment, other accessories such as earphones, VR glasses, somatosensory vibration feedback, etc. may be configured to match the user's habits or other application scenarios of the therapy mode. The module of the relaxation training can be customized by a user, and can also be intelligently generated according to the historical relaxation training effect of the user and the user data of the current scene.

The vibration sensor collects the original data of the vibration sensor while the driver performs relaxation training, calculates related parameters in real time and evaluates the mental state. After the training is finished, a related report of the training process is given, and the recovery condition of the mental state and the trend characteristics of the physiological parameters are reflected. On one hand, the module for relaxation training helps the driver to obtain a better relaxation effect than that of pure eye closure and spirit raising, on the other hand, the biofeedback evaluation result helps the driver to evaluate the self state and objectively evaluate the subsequent sustainable driving ability, namely the driving endurance index of the driver. The driving endurance index is generated according to the data recorded in the training process, such as whether the mental state is restored to the acceptable interval range, and such as whether the mental state is restored to the acceptable interval range and is stable (such as lasting for 15 minutes). In one embodiment, the driving endurance index may also be modified based on the type of relaxation training module and the duration of the relaxation training. The driver can more effectively evaluate the subsequent sustainable driving ability of the driver according to the subjective feeling and objective data of the driver and decide whether to start again. Of course, if the objective data are obviously abnormal, the driver can be warned, and the driver can confirm the self state.

Based on the collected original signals of the vibration sensor, parameters such as respiratory frequency, respiratory mode and the like can be extracted, and heart impact waveform analysis and calculation of heart rate and heart rate variability time-frequency parameters can be extracted, so that real-time calculation can be realized, and the parameters can be used for subsequent display, storage, recording or transmission; based on one or more of the parameters, different combinations are carried out, mental stress index evaluation models and fatigue index evaluation models suitable for different scenes can be further constructed, and real-time calculation can be carried out for subsequent display, storage, recording or transmission; meanwhile, the in-position state of the driver can be monitored, the rest or training time can be analyzed, a plurality of sensors can be added to monitor different sitting positions such as forward leaning, backward leaning, left leaning and right leaning states, and the state can be calculated in real time and used for subsequent display, storage, recording or transmission. The driver can preview the relevant data on the vehicle-mounted navigation terminal C, and can also preview the relevant data in a mobile phone mode, a tablet personal computer mode, a webpage end mode and the like.

In contrast to the driving process in the foregoing embodiment 1, evaluated here is the driving endurance index DEI recovery process, which is a process of continuously accumulating the driving ability, i.e., the driving endurance index, during the resting or relaxation training of the driver. And generating a driving endurance index curve of the driving endurance index changing along with time according to the monitored physiological parameters and behavior information of the driver and a preset initial driving endurance index DEI (t0), and not giving an early warning when the driving endurance index meets the condition that the driver travels again. And if the driving endurance index is still in the interval range of improper continuous driving, giving an early warning prompt if the driver needs to give out the vehicle again, and recording an early warning event. Of course, the driver can make his own judgment according to the subsequent driving task, for example, only a very short mileage disconnection is needed to be driven subsequently, and the system may properly reduce the early warning level according to the early warning configuration of the driver. Of course, the priority principle is also a safety principle, but does not exclude the subjective control of the driver himself.

In the simplest embodiment, it is assumed that only the driving endurance index model related to the stress index is established. In one embodiment, Stress index Stress (HR (t)) may be simply mapped as the mean of heart rate over time, representing higher Stress as the heart rate is higher and lower Stress as the heart rate is lower and tends to stabilize. In one embodiment, Stress index Stress (rr (t)) may be simply mapped as the mean of the breathing rate over a period of time, with higher breathing rates representing higher Stress and lower breathing rates tending to stabilize. In the embodiment, the heart rate variability is used for calculation, which reflects the synergistic effect of the sympathetic nerve and the parasympathetic nerve of the autonomic nervous system, represents the function and the balance capability of the autonomic nervous system, and can reflect the mental state of the patient. There are many analysis methods for heart rate variability, including linear analysis methods and nonlinear analysis methods, and linear analysis methods also include time domain analysis methods, frequency domain analysis methods, transfer function analysis methods, and the like. In this embodiment, a frequency domain analysis method is adopted, and based on the obtained time domain BCG signal waveform, a beat-to-beat heart beat width sequence is obtained by a wave searching method, and a heart beat width sequence of a certain time length (for example, 2 minutes or 5 minutes) is taken for power spectrum analysis. The power spectrum can be obtained by using methods such as Fourier transform, Welch spectrum method, AR spectrum estimation and the like. In the embodiment, an AR spectrum estimation method is adopted, then spectrum division is carried out, and grouping classification is carried out on a high-frequency component HF of 0.15-0.40 Hz, a low-frequency component LF of 0.04-0.15 Hz and an ultra-low-frequency component VLF of 0.003-0.04 Hz. The energy ratio LF/HF of the low frequency component to the high frequency component is calculated, which reflects the state of equilibrium of the autonomic nervous system, thereby mapping Stress index Stress (HRV (t)), HRV (t) = HRV ((LF/HF) (t)). Further, in one embodiment, the Stress index Stress (HRV (t)), (HRV (t)) = HRV ((LF/HF) (t), TP (t)) may be modified in combination with the total power spectrum TP.

In one embodiment, Stress (hr (t), rr (t), hrv (t)) can be calculated comprehensively from the heart rate, respiratory rate, and heart rate variability to comprehensively consider the influence of each parameter on the mental state of the patient. In one embodiment, stress (t) can be calculated comprehensively through more other parameters at the same time, so as to comprehensively consider the influence of multiple parameters on the mental state of the patient.

In the embodiment, the mental stress index value is mapped to be 0-100 points, the larger the numerical value is, the more stress is felt, 0-20 means that the stress is good, 20-40 means that the stress is acceptable, 40-60 means that the stress is slightly felt, 60-80 means that the stress is medium, and 80-100 means that the stress is severe. In one embodiment, the mental stress index can be expressed as A-H gears, 1-5 gears and the like, and various representation modes can be adopted as long as the mental stress states with different scores or intervals can be expressed in a distinguishing manner. Fitting a functional relationship between the recovery of the driving endurance index DEI and the mental stress, such as a polynomial function, an exponential function, piecewise fitting, nonlinear fitting, and the like, wherein an expression and a coefficient of the fitting function can be obtained based on various data (source) statistical methods. It is not established as a piecewise fitting function:

if 0 < MSI (t) ≦ 20, δ dei (t) = f1(MSI (t));

if 20 < MSI (t) ≦ 40, δ dei (t) = f2(MSI (t));

if 40 < MSI (t) ≦ 60, δ dei (t) = f3(MSI (t));

if 60 < MSI (t) ≦ 80, δ dei (t) = f4(MSI (t));

if 80 < MSI (t) ≦ 100, δ dei (t) = f5(MSI (t));

each piecewise function may also be fitted to the actual data (source) using methods such as polynomial functions, exponential functions, piecewise fitting, nonlinear fitting, and the like. Fig. 8 shows the variation curve of the stress index during the relaxation training of a driver, and the driving endurance index curve updated accordingly. For clarity of illustration, the present embodiment performs vertical coordinate matching on the two data. The driving endurance index DEI (t0) is initially low and does not support the driver to better continue driving, while the stress index MSI (t0) is high. The driver performs a relaxation training with a period duration of T = T, the parameters of the whole process recorded in fig. 8 varying. It can be seen that as the relaxation training continues, the stress index gradually decreases from the high level line and then fluctuates up and down the low level line; accordingly, the driving endurance index is accumulated and reserved, and gradually increased. When t = t1, the driving endurance index is restored to DEI (t1), and when t = t2, the driving endurance index is restored to DEI (t 2). If the system estimates that the subsequent driving behavior needs to be DEI (=) = DEI (t 2). If the driver finishes relaxing training (or stops resting) and wants to continue driving for a trip at the time t = t1, the system judges that the driving endurance index of the driver still cannot support the driver to complete the next driving task (or is in the range of the unsuitable interval for continuing driving), the driver gives an early warning prompt, and the early warning event is recorded. Of course, the driver can make his own judgment according to the subsequent driving task, for example, only a very short mileage disconnection is needed to be driven subsequently, and the system may properly reduce the early warning level according to the early warning configuration of the driver. Of course, the priority principle is also a safety principle, but does not exclude the subjective control of the driver himself. And if the driver finishes the relaxation training (or stops the rest) and wants to continue driving for traveling at the time of t = t2, the system judges that the driving endurance index of the driver is restored to a reasonable level at the time, no early warning is given, and the related report driver can preview the driving endurance index by himself or set a pop-up window or voice prompt according to the driver himself. In this embodiment, the driver continues to relax and train after the time T2 until the time T = T (T > T2) is completed, and the driving endurance index is restored to be higher than DEI (x), so that no early warning is given, and the driver can go out safely and stably according to the subjective feeling and the objective data report of the driver.

In one embodiment, associated massage functions may also be configured to assist the driver in relaxing. In one embodiment, a seat heating function may also be configured to assist the driver in relaxation. In one embodiment, the vehicle interior environment matching function, such as fragrance lamp control, temperature control, light control and the like, can be further configured to help the driver relax.

Of course, after the driver drives the road again, the subsequent real-time monitoring is continuously carried out, the physiological parameters and the behavior characteristics of the driver are continuously recorded, and the driving endurance index of the driver is continuously updated, namely, the scene of returning to the embodiment 1 is equivalent to, and only the preset initial driving endurance index is replaced by the driving endurance index recovered by the current short rest or relaxation training. Meanwhile, the driving endurance index model can be corrected based on the short-term rest or relaxation training process, a preset system early warning threshold state set is corrected, the early warning foresight and accuracy are improved, and the safety is further guaranteed. For example, the driver stops the relaxation training at t = t1, warning that it may be driving with insufficient recovery of endurance index, but the driver is still traveling. In the process of going on a trip, the driving endurance index is lost more quickly than the original model, and the early warning state is achieved in a shorter time so as to better ensure the driving safety of the driver.

Example 4: sleep monitoring feedback

When the driver drives for a long distance, especially a driver of a large vehicle, it is likely that the vehicle is the second 'home', and work and rest are basically completed on the vehicle, including sleeping. Or multiple drivers alternately drive for a long distance in a crossed way, and the drivers need to alternately take a rest. In this case, unlike the short relaxation training mode, the driver needs a longer sleep recovery time.

In this embodiment, after the vibration sensor is deployed in the vehicle, a sleep monitoring function may be integrated to monitor various indexes of the driving seat or the passenger seat, such as sleep state, sleep quality, sleep stage, and mental state recovery during sleep. In one embodiment, the driver may be sleeping at the driver's seat; in one embodiment, a driver may cross-drive a sleep break with another driver at a front passenger location; in one embodiment, the driver of the cart may lie on the rear seats for sleep and rest; in one embodiment, a driver of a caravan may sleep and rest on a certain bed.

After the sleep is finished, the driver can obtain a related report of the sleep process, the recovery condition of the mental state and the trend characteristics of the physiological parameters are reflected, the biofeedback evaluation result helps the driver to evaluate the self state, and the subsequent sustainable driving ability, namely the driving endurance index of the driver, is objectively evaluated. The driving endurance index is generated according to data recorded in the sleep process, such as one or more of the indexes of sleep state, sleep quality, sleep stage, sleep duration, mental state recovery of the sleep process and the like. The driver can more effectively evaluate the subsequent sustainable driving ability of the driver according to the subjective feeling and objective data of the driver, and decide whether to restart or exchange the driver. Of course, if the objective data are obviously abnormal, the driver can be warned, and the driver can confirm the self state.

In contrast to the driving process in the foregoing embodiment 1, evaluated here is the driving endurance index DEI recovery process, during which the driver's sleep is recovered, the driving ability is continuously accumulated, i.e., the driving endurance index is accumulated. And generating a driving endurance index curve of the driving endurance index changing along with time according to the monitored physiological parameters and behavior information of the driver and a preset initial driving endurance index DEI (t0), and not giving an early warning when the driving endurance index meets the condition that the driver travels again. And if the driving endurance index is still in the interval range of improper continuous driving, giving an early warning prompt if the driver needs to give out the vehicle again, and recording an early warning event. Of course, the driver can make his own judgment according to the subsequent driving task, for example, only a very short mileage disconnection is needed to be driven subsequently, and the system may properly reduce the early warning level according to the early warning configuration of the driver. Of course, the priority principle is also a safety principle, but does not exclude the subjective control of the driver himself.

In the simplest embodiment, it is assumed that only the driving endurance index model related to Sleep stage Sleep is established. According to international standards, sleep stages can be divided into a wake stage, a light sleep stage N1, a light sleep stage N2, a deep sleep stage N3, and a rapid eye movement REM stage. It is of course also possible to simplify to combine the light sleeps N1 and N2 into one zone, or to simply distinguish between waking and falling asleep. In this embodiment, these five sleep stage states are taken. And fitting a functional relation between the recovery of the driving endurance index DEI and the Sleep stage Sleep, such as a polynomial function, an exponential function, piecewise fitting, nonlinear fitting and the like, wherein an expression and a coefficient of the fitting function can be obtained based on a plurality of data (source) statistical methods. It is not established as a piecewise fitting function:

δ dei (t) = g1(Sleep (t)) if Sleep is awake;

δ dei (t) = g2(Sleep (t)) if Sleep is stage N1;

δ dei (t) = g3(Sleep (t)) if Sleep is stage N2;

δ dei (t) = g4(Sleep (t)) if Sleep is stage N3;

δ dei (t) = g5(Sleep (t)) if Sleep is REM stage;

each piecewise function may also be fitted to the actual data (source) using methods such as polynomial functions, exponential functions, piecewise fitting, nonlinear fitting, and the like. Fig. 9 shows a sleep stage variation curve during sleep recovery of a driver, and a driving endurance index curve updated accordingly. For clarity of illustration, the present embodiment performs vertical coordinate matching on the two data. The driving endurance index DEI (t0) is low at the beginning, and the driver cannot be supported to better perform continuous driving, and the driver is in an awake state Sleep (t0) = Wake. The driver performs sleep recovery for a period of time T = T, the parameters of the entire process recorded in fig. 9 varying. It can be seen that as sleep recovery continues, the driver fluctuates from awake to light sleep N1 and N2, then goes to deep sleep N3, then to REM, then back to light sleep and finally awake; accordingly, the driving endurance index is accumulated and reserved, and gradually increased. When t = t1, the driving endurance index is restored to DEI (t1), and when t = t2, the driving endurance index is restored to DEI (t 2). If the system estimates that the subsequent driving behavior needs to be DEI (=) = DEI (t 2). If the driver finishes the sleep recovery (alarm or awakens at an event) and wants to continue driving at the moment of t = t1, the system judges that the driving endurance index of the driver still cannot support the driver to complete the next driving task (or is in the interval range of improper continuous driving), the driver gives an early warning prompt, and the early warning event is recorded. Of course, the driver can make his own judgment according to the subsequent driving task, for example, only a very short mileage disconnection is needed to be driven subsequently, and the system may properly reduce the early warning level according to the early warning configuration of the driver. Of course, the priority principle is also a safety principle, but does not exclude the subjective control of the driver himself. And if the driver finishes the sleep recovery and wants to continue driving for traveling at the time of t = t2, the system judges that the driving endurance index of the driver is recovered to a reasonable level, no early warning is given, and the related report driver can preview the report by himself or set a pop-up window or voice prompt according to the driver himself. In this embodiment, the driver also sleeps and recovers after the time T2 until the time T = T (T > T2) is finished, the driving endurance index is recovered to be higher than DEI (one), and therefore, no early warning is given, and the driver can go on a safe and stable trip according to the subjective feeling and the objective data report of the driver.

In one embodiment, an associated massage function may also be configured to assist the driver in sleep recovery. In one embodiment, a seat heating function may also be configured to assist the driver in sleep recovery. In one embodiment, the vehicle interior environment matching function, such as fragrance lamp control, temperature control, light control and the like, can be further configured to help the driver to recover from sleep.

Of course, after the driver drives the vehicle again, the subsequent real-time monitoring is still continuously performed, the physiological parameters and the behavior characteristics of the driver are continuously recorded, and the driving endurance index of the driver is continuously updated, namely, the scene of returning to the embodiment 1 is equivalently performed, and only the preset initial driving endurance index is replaced by the driving endurance index of the current sleep recovery. Meanwhile, the driving endurance index model can be corrected based on the sleep recovery process, a preset system early warning threshold state set is corrected, the early warning foresight and accuracy are improved, and the safety is further guaranteed. For example, the driver stops sleep recovery when t = t1, warns that it is likely that the driving endurance index recovery degree is insufficient, but the driver is still traveling. In the process of going on a trip, the driving endurance index is lost more quickly than the original model, and the early warning state is achieved in a shorter time so as to better ensure the driving safety of the driver.

In one embodiment, the vibration sensor may also be deployed in the driver's home, or portable plug and play deployed in a hotel to obtain relevant data. In one embodiment, when the sleep data can be obtained through other devices or technical schemes, for example, the sleep data is obtained through a wearable watch bracelet, and then the data interface is opened. Therefore, the night sleep data are integrated to compensate and calculate the safety model of the driving trip, otherwise, the trip data in the daytime can compensate and calculate the recovery model of the night sleep, and a full-flow data link is established, so that the method is more favorable for helping a driver to perform good self-evaluation management and protecting driving for the healthy and safe trip of the driver.

Example 5: more data applications

Embodiments 1, 3 and 4 of the present invention illustrate the self-defined configuration of a preset driving endurance index of a driver, the acquisition of a preset driving endurance index of a driver based on a sleep data state set before the driver drives, and the acquisition of data after the data is continuously accumulated can be performed according to a big data method. In one embodiment, the statistical state set may be obtained based on historical driver data, assuming that a driver does not switch on monitoring data before a certain trip, assuming that the statistical characteristic of the preset value of the driver in the previous three months is mean (dei) ± sd (dei), the recommendation of the preset value may be set to mean (dei) based on the characteristic, and of course, the driver may customize the adjustment based on the above. But the user-defined set value has a safety boundary and cannot exceed a reasonable range. The boundary of the reasonable range can also be obtained by statistics according to a big data method, such as not higher than 90% of the preset value in all the initial values of the previous three months.

In one embodiment, the preset driving endurance index calculated based on the statistical state set of real world big data, for example, the monitoring data of 10 ten thousand people in a certain area, is mediam (dei), and assuming that a certain driver does not switch on the monitoring data, the preset value recommendation can be set to mediam (dei), and of course, the driver can customize, change and adjust the preset value. But the user-defined set value has a safety boundary and cannot exceed a reasonable range. The boundary of the reasonable range can also be obtained by statistics according to a big data method, such as the preset value of not higher than 90% of drivers in 10 thousands of people in a certain area.

In one embodiment, it may also be possible to obtain based on an integrated model state set of real world big data and personalized data, i.e. consider mean (dei) and mediam (dei) simultaneously. In one embodiment, the driving endurance index may be obtained based on more of the above data, for example, the sleep data is monitored, and the driving endurance index is calculated as sleep (dei), and the minimum value/median value/maximum value is taken to be preset in combination with mean (dei) and media (dei).

The invention mainly describes the application of monitoring behaviors and health data of the vibration sensor, and actually, related data can be obtained in other modes such as wearing a monitoring watch or a bracelet (PPG monitoring), camera (image monitoring), electrocardiogram monitoring (ECG monitoring) and the like, and partial parameters in the invention can be obtained as well or all parameters in the invention can be obtained by combination application, and the like, and the method can be easily analogized by persons in the field.

This scheme possesses following advantage:

1. meanwhile, the health condition, the mental state and the behavior condition of a driver and passengers are concerned, and the technical paths are integrated and unified, so that the realization is convenient; the system can be separately deployed (any one or more seats), can be fully deployed (full seats) and has high degree of freedom.

2. The method integrates physiological parameter monitoring and behavior monitoring, and not only pre-warns the possible safety events from abnormal physical signs, but also pre-warns the possible safety events from abnormal behaviors;

3. user images such as facial appearance and fingerprint data are not collected, and the data are stored in a physiological fingerprint form, so that the privacy is respected, and the security level is high;

4. the fatigue driving monitoring and early warning system and the relaxation training system for helping mental recovery are integrated, and the relaxation training system is coupled with physiological parameter feedback, so that the recovery effect is enhanced, and the evaluation effect is assisted;

5. integrating a real-time early warning scheme and an early warning scheme, and establishing a more stable safety model;

6. the early warning in the vehicle and the early warning outside the vehicle can be triggered, so that the surrounding environment objects are warned while the internal potential safety hazard is avoided, and the capability of coping with emergencies is enhanced;

7. the monitoring, early warning and therapy are integrated, can be used independently and jointly, and the system architecture is modularized;

8. integrating driving data and sleeping data, establishing an all-weather data set, mining and establishing an all-weather model, and protecting driving and navigating for a user;

9. integrating the data of the whole Internet of vehicles, establishing a real world mass data set, establishing a state set based on mass data, and combining the state set with personalized data.

The foregoing describes in detail a system and a method for monitoring health and behavior of a vehicle user based on vehicle networking data informatization, and for those skilled in the art, there may be changes in the specific implementation manner and the application scope according to the idea of the embodiment of the present invention.

33页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种远程肌力自助康复检测装置

Automobile user health and behavior monitoring system and method based on Internet of vehicles data informatization

相关技术

网友询问留言