A vehicle-mounted health monitoring system and automobile product

Abstract

The application discloses a kind of vehicle health monitoring system and automobile product, vehicle health monitoring system includes internal communication module, driving event detection module and processing module, internal communication module receives the time curve of the sign data detected by intelligent wearable device to the personnel on the car, processing module obtains first health risk information to the time curve of sign data, obtains second health risk information to the time curve of sign data and first driving event, obtains third health risk information to the first health risk information and second health risk information.Processing is carried out to the time curve of sign data and first driving event in the case where the overall morbidity risk of driver is higher, and the above unit or personnel is automatically helped, so as to provide greater possibility for driver to obtain rescue in the case where driver is disabled and cannot manually help, and the life safety and traffic safety of driver and other personnel on the car are guaranteed.The application is widely used in the field of automobile technology.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to an in-vehicle health monitoring system and automotive products. Background Technology

[0002] While driving, if a driver suddenly suffers from an acute illness such as cardiovascular or cerebrovascular disease, it not only threatens the driver's life but may also cause the vehicle to lose control, thus affecting traffic safety. This risk is more pronounced when a driver is alone for an extended period of time, because if an acute illness occurs while driving alone, it is difficult for bystanders to notice, and the driver may not be able to call for help.

[0003] To mitigate these risks, some automotive technologies incorporate emergency call systems. Drivers can trigger the system with a single button when experiencing a sudden acute illness or feeling unwell. The system detects the vehicle's real-time location and generates a distress signal, which is then sent to rescue organizations and other relevant departments. This allows rescue organizations and other departments to provide timely assistance to the driver and ensure their safety.

[0004] However, even with an emergency call system in place, the driver needs to actively activate it. Acute illnesses often develop very rapidly, leaving drivers with very little reaction time. Furthermore, the driver's discomfort can be masked by their focus on driving, leading to a rapid onset of illness and incapacitation after the driver experiences discomfort. This leaves no time to activate the emergency call system, rendering it ineffective. Summary of the Invention

[0005] In view of at least one of the above-mentioned technical problems, the purpose of this invention is to provide an in-vehicle health monitoring system and an automotive product.

[0006] On one hand, embodiments of the present invention include an in-vehicle health monitoring system, the in-vehicle health monitoring system comprising: Internal communication module; The internal communication module is used to communicate with the smart wearable devices worn by the people in the vehicle and to receive the time curve of the vital signs data detected by the smart wearable devices. Driving event detection module; The driving event detection module is used to detect the first driving event of the vehicle; The first driving event includes events in which the occupants operate the vehicle, as well as external events in the traffic environment in which the vehicle is located; The processing module is used to process the time curve of vital sign data to obtain the first health risk information, process the time curve of vital sign data and the first driving event to obtain the second health risk information, and process the first health risk information and the second health risk information to obtain the third health risk information.

[0007] Furthermore, the time curves of vital sign data are processed to obtain primary health risk information, including: The first curve segment was determined from the time curve of vital signs data using the sliding window method. Perform feature recognition on the first curve segment to obtain the first abnormal feature information; Based on the first abnormal feature information, the first health risk information is determined.

[0008] Furthermore, the detection of the car's first driving event includes: Whenever a driving event is detected, the event type of the driving event is detected, the driving event is recorded as a first driving event, and the detection time and event type of the first driving event are recorded.

[0009] Furthermore, processing the time curves of vital sign data and the first driving event yields secondary health risk information, including: From all the first driving events, identify several second driving events; each second driving event is a first driving event whose corresponding event type is the target type. Based on the detection time corresponding to each second driving event, the time curve of vital signs data is divided into several second curve segments; Feature recognition is performed on the last second curve segment to obtain the second abnormal feature information; Based on the second abnormal feature information, the second health risk information is determined.

[0010] Furthermore, from all the first driving events, several second driving events are identified, including: Detect the real-time location information of the vehicle; Based on real-time location information, determine specific target events in the scene; Define the event type of a specific target event in the scene as the target type; The first driving event, whose corresponding event type is the target type, is identified as the second driving event.

[0011] Furthermore, from all the first driving events, several second driving events are identified, including: Iterate through all event types corresponding to all first-drive events; For any event type, obtain the periodicity of the time sequence formed by arranging each first driving event of the event type according to the detection time; Get the maximum value among all periodicity levels; The event type corresponding to the maximum value is determined as the target type; The first driving event, whose corresponding event type is the target type, is identified as the second driving event.

[0012] Furthermore, the first and second health risk information are processed to obtain the third health risk information, including: Determine the weighting weights; The second health risk information is weighted according to the weighting method and then superimposed on the first health risk information to obtain the third health risk information.

[0013] Furthermore, determining the weighting weights includes: Obtain the overlap between the last second curve segment and the first curve segment; The weighting is determined based on the degree of overlap and positive correlation.

[0014] Furthermore, the in-vehicle health monitoring system also includes: Smart wearable devices; External communication module; the external communication module is used to send third-party health risk information to the rescue terminal.

[0015] On the other hand, embodiments of the present invention also include an automotive product, the automotive product including the in-vehicle health monitoring system described in the embodiments.

[0016] The beneficial effects of the present invention are: the vehicle health monitoring system in the embodiment can automatically request assistance from the aforementioned units or personnel when the driver's overall risk of illness is high, thereby providing a greater possibility for the driver to receive assistance in the event that the driver becomes disabled due to illness and is unable to manually request assistance, thus ensuring the life safety and traffic safety of the driver and other passengers in the vehicle. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the vehicle-mounted health monitoring system in the embodiment; Figure 2 This is a schematic diagram of the smart wearable device in the embodiment; Figure 3 This is a schematic diagram of the time curve of vital sign data in the embodiment; Figure 4 This is a schematic diagram of the steps of the vehicle-mounted health monitoring method in the embodiment; Figure 5 This is a schematic diagram illustrating the principle of step S1 in the embodiment; Figure 6 This is a schematic diagram illustrating the principle of steps S201-S204 in the embodiment. Detailed Implementation

[0018] This embodiment provides an in-vehicle health monitoring system. The in-vehicle health monitoring system can be installed in a vehicle, forming an integrated unit with other components of the vehicle. (Refer to...) Figure 1The vehicle health monitoring system includes a processing module, an internal communication module, and a driving event detection module. In addition, a positioning and navigation module and an external communication module can also be set up.

[0019] The processing module is a module with functions such as data acquisition, data processing, data output, and control. For example, an Electronic Control Unit (ECU) can be used as the processing module. The internal communication module is a module that can communicate with user terminals such as smart wearable devices and mobile phones via low-power short-range wireless communication protocols such as Bluetooth.

[0020] In this embodiment, the smart wearable device specifically refers to a smartwatch or similar device. (Refer to...) Figure 2 Drivers of cars equipped with in-vehicle health monitoring systems wear smart wearable devices while driving, bringing these devices into contact with their bodies. The smart wearable devices use sensors such as heart rate sensors, blood oxygen saturation sensors, and blood pressure sensors to detect vital signs such as heart rate, blood oxygen saturation, and blood pressure.

[0021] In this embodiment, the smart wearable device performs periodic detection at a certain sampling rate to obtain multiple heart rate data points. A heart rate time curve is generated based on the sampling time of the heart rate data. Based on the same principle, the smart wearable device can generate blood oxygen concentration time curves and blood pressure time curves. Heart rate time curves, blood oxygen concentration time curves, and blood pressure time curves are all types of vital sign data time curves. In this embodiment, the heart rate time curve is used as an example of a vital sign data time curve for illustration. One form of a vital sign data time curve is as follows... Figure 3 As shown.

[0022] In this embodiment, the smart wearable device sends the vital sign data time curve to the internal communication module via the Bluetooth communication protocol. Specifically, the smart wearable device can simultaneously collect vital sign data, generate vital sign data time curves, and send the vital sign data time curves, enabling the internal communication module to obtain the latest vital sign data time curves in real time.

[0023] In this embodiment, refer to Figure 1 The driving event detection module includes an in-vehicle event detection unit and an external event detection unit. The in-vehicle event detection unit specifically includes sensors such as an accelerator pedal sensor and a steering wheel sensor, while the external event detection unit specifically includes sensors such as a lane position sensor, a light intensity sensor, and a neighboring vehicle position sensor.

[0024] Specifically, the in-vehicle event detection unit can detect events where the driver or other occupants perform specific operations on the vehicle. For example, the accelerator pedal sensor can detect the depth of the accelerator pedal, thus detecting events such as "the driver presses the accelerator pedal from 0 to 20% depth," which indicates a light press of the accelerator, and the corresponding event type is "light press of the accelerator." Alternatively, it can detect events such as "the driver presses the accelerator pedal from 0 to 80% depth," which indicates a deep press of the accelerator, and the corresponding event type is "deep press of the accelerator." Similarly, the steering wheel sensor can detect the steering wheel rotation angle, thus detecting events such as "the driver turns the steering wheel 30° to the left," which indicates a slow turn of the steering wheel, and the corresponding event type is "slow turn to the left," or "the driver turns the steering wheel 120° to the right," which indicates a sharp turn of the steering wheel, and the corresponding event type is "sharp turn to the right."

[0025] Specifically, the external event detection unit can detect external events occurring in the traffic environment where the vehicle is located, or external events that occur due to the interaction between the vehicle and the traffic environment. For example, a lane position sensor can detect which lane the vehicle is traveling in, thus detecting events such as "the vehicle has moved one lane to the right," which corresponds to the event type "changing lanes to the right," or "the vehicle has moved one lane to the left," which corresponds to the event type "changing lanes to the left." A light intensity sensor can identify natural light such as sunlight, as well as light emitted by streetlights or other vehicle lights, and detect the intensity of these lights, thus detecting events such as "the intensity of sunlight or streetlight light has decreased to half," which typically corresponds to the vehicle entering a tunnel. The corresponding event type for areas with roads or shade is "reduced ambient light," or the detection of events such as "the intensity of a vehicle's headlights rises from the first threshold to the second threshold and then falls back to the first threshold." Such events usually correspond to a vehicle with its headlights on passing in the opposite direction, and the corresponding event type is "external vehicle headlights sweep past." The vehicle position sensor can detect the presence of a vehicle and its position relative to the vehicle itself, thereby detecting events such as "a vehicle in front moves backward relative to the vehicle and becomes the vehicle behind." Such events usually correspond to the vehicle overtaking the vehicle in front, and the corresponding event type is "overtaking."

[0026] Therefore, the driving event detection module can detect various types of driving events, the content and types of which are shown in Table 1.

[0027] Table 1

[0028] In this embodiment, the driving event detection module can continuously detect driving events during the vehicle's operation. Each time a driving event from Table 1 is detected, it is recorded as a first driving event, along with the event type and the time of detection. As the driving process continues, the driving event detection module can detect multiple first driving events.

[0029] In this embodiment, when a specific point in time is reached, such as the current time, t present The driving event detection module detected the first driving event 1, the first driving event 2, ... the first driving event. m wait m There are 10 first driving events, arranged in chronological order of detection time. Since these first driving events are the raw data detected by the driving event detection module, the above... m The first driving event is generally a mixed sort of various event types.

[0030] In this embodiment, the processing module can execute an on-board health monitoring method. (Refer to...) Figure 4 The in-vehicle health monitoring method includes the following steps: S1. Process the time curve of vital signs data to obtain the first health risk information; S2. Process the time curve of vital signs data and the first driving event to obtain the second health risk information; S3. Process the first and second health risk information to obtain the third health risk information.

[0031] In this embodiment, when the processing module executes step S1, it processes the received real-time updated vital sign data time curve using a sliding window method. Specifically, refer to... Figure 5 The processing module sets a sliding time window, which corresponds to a fixed duration. T And keep sliding forward, so that as the vital signs data time curve is updated, the sliding time window can always slide to the latest current time point. t present The starting point is determined at [location]. t present - T The endpoint is t present The time period. In this embodiment, the starting point of the latest position of the sliding time window is... t present - T The endpoint is t present The time curve of the corresponding vital signs data within the specified time period is determined as the first curve segment.

[0032] In this embodiment, when the processing module executes step S1, it can use the physical signs and data characteristics of the onset precursors of acute diseases such as cardiovascular and cerebrovascular diseases determined by medical research as the detection target to perform feature recognition on the first curve segment.

[0033] For example, medical research shows that the heart rate of a normal healthy person is stable. Therefore, when a driver does not experience an acute illness, the time curve of the detected vital signs data, as well as the first curve segment, is also stable. This is manifested in the fact that the time domain characteristics such as the instantaneous heart rate (HR) of the first curve segment are within a normal range, and the frequency domain characteristics such as the ratio of low-frequency components to high-frequency components (LF / HF) are less than 1. However, before a driver with cardiovascular and cerebrovascular diseases develops an illness, the first curve segment detected will show abnormal characteristics of instability, such as the instantaneous heart rate being lower or higher than the normal range, and the LF / HF being greater than 1.

[0034] In this embodiment, abnormal features that are determined to be characteristic of vital signs through medical research can be stored in the processing module. When the processing module executes step S1, after performing spectral extraction and other processing on the first curve segment, it detects whether these abnormal features exist, thereby determining whether the driver is at risk of developing acute diseases such as cardiovascular and cerebrovascular diseases, and representing the determination result as the first health risk information.

[0035] For example, the number of abnormal features detected in step S1 can be calculated as a proportion of the total number of abnormal features that could be detected in step S1 (i.e., the abnormal features stored in the processing module), thereby quantitatively representing the first health risk information. For example, if no abnormal features are identified from the first curve segment, then a first health risk information of size 0 can be generated, indicating that the driver is identified as being at a certain point in time based on the first curve segment. t present If the driver exhibits few early signs of acute illness, the risk of illness in the near future is considered low, indicating "low risk". If half of the abnormal features stored in the processing module are identified from the first curve segment, a first health risk information of 50% can be generated, indicating a moderate risk of illness in the near future, indicating "medium risk". If all abnormal features stored in the processing module are identified from the first curve segment, a first health risk information of 100% can be generated, indicating a high risk of illness in the near future, indicating "high risk".

[0036] In this embodiment, when the processing module executes step S2, which is to process the time curve of vital sign data and the first driving event to obtain the second health risk information, it can specifically perform the following steps: S201. From all the first driving events, identify several second driving events; S202. Based on the detection time corresponding to each second driving event, the vital signs data time curve is divided into several second curve segments; S203. Perform feature recognition on the last second curve segment to obtain the second abnormal feature information; S204. Determine the second health risk information based on the second abnormal feature information.

[0037] The principle of steps S201-S204 is as follows: Figure 6 As shown.

[0038] Reference Figure 6 In step S201, from the first driving event 1, the first driving event 2... the first driving event m wait m From the first driving events, select some or all of the first driving events to obtain... n The first driving incident, and on this n The first driving incidents were arranged in chronological order of their original detection times, becoming... n The second driving incident.

[0039] In this embodiment, when performing step S201, the following steps can be specifically performed: S20101A. Traverse all event types corresponding to all first-drive events; S20102A. For any event type, obtain the periodicity of the time sequence of each first driving event corresponding to the event type arranged according to the detection time; S20103A. Obtain the maximum value among all periodicity levels; S20104A. Determine the event type corresponding to the maximum value as the target type; S20105A. The first driving event with the corresponding event type of the target type is identified as the second driving event.

[0040] Steps S20101A-S20105A are the first execution method of step S201.

[0041] In steps S20101A-S20102A, refer to the various event types shown in Table 1, starting with the first driving event 1, the first driving event 2, and so on. m wait m From the first driving events, select all first driving events belonging to the "lightly pressing the accelerator" event type and arrange them into time sequence 1; then start from first driving event 1, first driving event 2... first driving event m waitm In the first driving event, select all first driving events that belong to the event type of "pressing the accelerator hard" and arrange them into time sequence 2... to obtain multiple time sequences. The first driving events in each time sequence are the same event type.

[0042] In step S20102A, the periodicity of each time series can be calculated separately. In this embodiment, the periodicity indicates the degree to which the time series has a periodicity. Specifically, the periodicity can be measured by calculating indicators such as the maximum autocorrelation coefficient (the larger the value, the greater the periodicity) or the autocorrelation significance ratio (the larger the value, the greater the periodicity).

[0043] By executing step S20102A, the degree of periodicity of the time series corresponding to each event type is determined. In steps S20103A-S20104A, the maximum value of all periodicities is determined, and the event type corresponding to the time series with periodicity is determined as the target type.

[0044] For example, assuming that the time sequence 2 of all the first driving events of the "deep acceleration" event type obtained by executing step S20102A has the greatest periodicity, then in step S20104A, the "deep acceleration" event type is determined as the target type.

[0045] In step S20105A, the current time point is... t present First driving event 1, first driving event 2... first driving event detected m wait m In the first driving event, the first driving event belonging to the target type is identified as the second driving event, that is, the above time series 2 is identified as the second driving event.

[0046] In this embodiment, by executing steps S20101A-S20105A, the current time point can be determined. t present Of all the detected first driving events, the one with the most regular time cycle is selected as the second driving event. Thus, the determined second driving events 1, 2, ... are named as follows: n wait n The second driving event indicates that the driver is at the current point in time. t present Driving events with a good time cycle pattern that were previously encountered in actual operation or in traffic environment.

[0047] In this embodiment, when performing step S201, the following steps can be specifically performed: S20101B. Detect the real-time location information of the vehicle; S20102B. Determine specific target events in the scene based on real-time location information; S20103B. Determine the event type of a scene-specific target event as the target type; S20104B. The first driving event with the corresponding event type of the target type is identified as the second driving event.

[0048] Steps S20101B-S20104B are the second execution method of step S201.

[0049] In step S20101B, the processing module can call the positioning and navigation module to detect the car's position at the current time point. t present The real-time location information. In step S20102B, the scene-specific target event to be determined by the processing module represents the driving event that the driver should operate or encounter in the scene corresponding to the real-time location information.

[0050] For example, if the real-time location information determined by step S20101B is in a gentle uphill environment, the processing module can query the corresponding scene-specific target event as "lightly pressing the accelerator" according to the locally stored mapping table. This means that under normal circumstances, the driver should regularly operate at this location to perform the driving event of "lightly pressing the accelerator" in a time cycle.

[0051] In steps S20103B-S20104B, the "lightly pressing the accelerator" determined in step S20102B is used as the target type, and the current time point is... t present First driving event 1, first driving event 2... first driving event detected m wait m In the first driving event, the first driving event belonging to the target type of "lightly pressing the accelerator" is identified as the second driving event, that is, the event type of the identified second driving events is "lightly pressing the accelerator".

[0052] In this embodiment, by executing steps S20101B-S20104B, the current time point can be determined. t present Of all the detected first driving events, the first driving event of the type that exhibits a time-periodic regularity at the current location is selected as the second driving event. Thus, the determined second driving events 1, 2, ... are: n wait nThe second driving event indicates that the driver is at the current point in time. t present Driving events with a good time cycle pattern that were previously operated or encountered in the traffic environment; moreover, the multiple second driving events obtained by executing steps S20101B-S20104B may all correspond to the same event type, or they may correspond to different event types.

[0053] In this embodiment, whether steps S20101A-S20105A or steps S20101B-S20104B are selected, multiple second driving events can be determined. These second driving events are events that occur to the driver at the current time. t present Driving events that exhibit a significant time-cycle pattern among all driving events performed or encountered.

[0054] In this embodiment, it is assumed that executing step S201 yields second driving event 1, second driving event 2, ... second driving event. n wait n The second driving event. In step S202, refer to Figure 6 Obtain the detection time of the second driving event 1. t 1. Detection time of the second driving incident 2 t 2...Second Driving Incident n -1 detection time t n-1 Second driving incident n Detection time t n These detection times define multiple dividing points on the time axis, thus allowing the vital signs data time curve to be divided into sections from... t 1 to t Part 2, from t 2 to t Part 3...from t n-1 arrive t n These parts are each considered as a second curve segment.

[0055] In step S203, the processing module processes the last second curve segment, which is the vital sign data time curve, from... t n-1 arrive t n Feature recognition is performed on certain parts.

[0056] In this embodiment, the processing module can first determine whether the time length of the last second curve segment is long enough. For example, the processing module can determine the length of the sliding time window. TSet as a duration threshold, representing the duration of the last second curve segment. t n - t n-1 Greater than or equal to the duration threshold T In this case, step S203 can be performed on the last second curve segment; within the time length of the last second curve segment t n - t n-1 Less than the duration threshold T In this case, the processing module can choose to extract the last two second curve segments, i.e., the vital sign data time curves, from... t n-2 arrive t n-1 Parts and from t n-1 arrive t n Parts are merged into the same second curve segment, and its duration is determined. t n - t n-2 Is it greater than or equal to the duration threshold? T If yes, then step S203 is executed on the merged second curve segment; otherwise, the search for the second curve segment continues. That is, the processing module finds the smallest positive integer. i , making t n - t n-i Greater than or equal to the duration threshold T And the time curve of vital signs data from t n-i arrive t n The entire portion is treated as the second curve segment and processed in step S203. This avoids the second curve segment being too short, resulting in insufficient information, and ensures that enough information is identified to obtain reliable second health risk information.

[0057] In this embodiment, the principle of steps S203-S204 is the same as that of step S1. Abnormal features identified through medical research can also be stored in the processing module. When the processing module executes steps S203-S204, after processing the second curve segment using methods such as spectrum extraction, it detects the presence of these abnormal features to determine whether the driver is at risk of developing acute diseases such as cardiovascular or cerebrovascular diseases. The result is then presented as second health risk information. The difference lies in that the object processed in step S1 is... Figure 5The first curve segment in the curve, the object to be processed in steps S203-S204 is Figure 6 The second curve segment in the diagram.

[0058] By performing steps S201-S204, second health risk information with values ​​ranging from 0-100% can be obtained.

[0059] In this embodiment, when the processing module executes step S3, which is to process the first health risk information and the second health risk information to obtain the third health risk information, it can specifically perform the following steps: S301. Determine the weighting weights; S302. After weighting the second health risk information according to the weighted weights, it is superimposed with the first health risk information to obtain the third health risk information.

[0060] In step S301, the weighting weight is the weight used to weight the second health risk information. In this embodiment, a small fixed value, such as 0.2, can be set as the weighting weight.

[0061] In step S302, the formula can be used. Third health risk information = First health risk information + Second health risk information × Weighted weight Thus, the third health risk information is calculated. With a fixed value, such as 0.2, used as the weighting factor, the formula for calculating the third health risk information is as follows: Third health risk information = First health risk information + Second health risk information × 0.2 In this embodiment, the external communication module can set multiple thresholds (e.g., 0.4 and 0.8). When the value of the third health risk information is less than 0.4, the driver's overall health risk is determined. For example, the risk of acute illness is low, and the external communication module can do nothing. When the value of the third health risk information is greater than 0.4 and less than 0.8, the driver's overall health risk is determined to be moderate. The external communication module can generate a prompt message with the content "Hello, the driver with license plate number xxx and name xxx is currently at the location of latitude and longitude coordinates xxx. A moderate risk of illness has been detected, and we are now issuing a warning to you." The third health risk information and the prompt message are sent to the rescue terminal. When the value of the third health risk information is greater than 0.8, the driver's overall health risk is determined to be high. The external communication module can generate a prompt message with the content "Hello, the driver with license plate number xxx and name xxx is currently at the location of latitude and longitude coordinates xxx. A high risk of illness has been detected, and he is likely to fall ill in a short time. We suggest you immediately confirm his safety and provide rescue if necessary." The third health risk information and the prompt message are sent to the rescue terminal.

[0062] In this embodiment, the rescue terminal can be a communication terminal used by the driver's workplace, a hospital or other medical institution, or the driver's emergency contact. The external communication module can automatically request assistance from these entities or individuals when the driver's overall risk of illness is high. This increases the likelihood of the driver receiving help should they become incapacitated due to illness and be unable to manually seek assistance, thereby ensuring their safety.

[0063] In this embodiment, the in-vehicle health monitoring system works as follows: The system communicates with smart wearable devices worn by the driver and other occupants, acquiring time curves of vital sign data detected by these devices to detect the first health risk. Leveraging the close contact between the smart wearable devices and the occupants, which allows for accurate detection of vital sign data, the system tracks health risks such as the risk of acute illnesses in real time. When a health risk is high, it automatically requests external assistance to ensure safety. Furthermore, the in-vehicle health monitoring system in this embodiment can detect the first health risk using common methods such as the sliding window method, serving as a basis for monitoring the driver's health. The basic health risk assessment results for drivers are obtained through observation without any additional conditions, representing the driver's "unconditional health risk." Based on this, the in-vehicle health monitoring system employs an algorithm that samples the time curve of vital sign data, different from the sliding window method. Specifically, the system detects driving events that the driver has recently performed or encountered and that exhibit a time-periodic pattern—the second driving event. It uses the detection time of the second driving event as a dividing point to segment the time curve of vital sign data, thereby determining the second curve segment to be detected. This utilizes the time-periodic nature of the second driving event, and... The potential correlation between the driver's acute illness events (e.g., the stimulating effect of a second driving event on the onset of the driver's acute illness, or the premonitory symptoms of the driver's acute illness being characterized as a second driving event) is detected as a second health risk information by a second curve segment determined based on the time window defined by the second driving event. This second health risk information is an additional detection result for the driver's health risk. This additional detection result is observed on the driver under the condition of "the occurrence of a second driving event," representing the driver's "conditional health risk." According to Bayes' theorem, since the second health risk information is calculated considering the potential correlation between the second driving event and the driver's acute illness events, the second health risk information has higher sensitivity than the first health risk information. By superimposing the first and second health risk information to obtain the third health risk information, the more sensitive second health risk information can be used as a correction term for the first health risk information to obtain a larger third health risk information, serving as a prudent assessment of the driver's health risk. By requesting help from the outside world based on the third health risk information, it is easier to trigger the process of sending the third health risk information to the rescue terminal, which can improve the prudence of processing the driver's vital signs data and ensure life safety.

[0064] In this embodiment, in addition to setting a fixed value as the weighting weight for weighting the second health risk information, it is also possible to calculate... Figure 5 The first curve segment shown is... Figure 6The overlap between the second curve segments is shown. In this embodiment, the distance between the midpoint of the time period corresponding to the first curve segment and the midpoint of the time period corresponding to the second curve segment can be calculated. The smaller the distance, the greater the overlap between the first and second curve segments. Based on the overlap, a positive correlation is used to determine the weighting weight, that is, based on the distance between the two midpoints, a negative correlation is used to determine the weighting weight. For example, it can be determined according to the formula...

[0065] The weighted weights are calculated. ,in The base of the natural index is . The distance between the two midpoints mentioned above. To eliminate the coefficients of the dimensionless, the distance between the two midpoints can be mapped to the interval (0,1] to obtain a weight greater than 0 and less than or equal to 1. This avoids the weight of the second health risk information being greater than that of the first health risk information, so that the second health risk information is always used as a correction term for the first health risk information.

[0066] In this embodiment, since the first curve segment and the second curve segment are obtained by dividing the same vital sign data time curve in different ways, the first curve segment and the second curve segment are generally inconsistent. The degree of overlap between the first curve segment and the second curve segment indicates the degree of consistency between them. The greater the degree of overlap between the first curve segment and the second curve segment, the more consistent they are. This means that the method of dividing the vital sign data time curve according to the second driving event is closer to the result obtained by the general method of dividing the vital sign data time curve. This indicates that the reference value of the second health risk information of the driver's "conditional health risk" is greater, that is, the second health risk information of "conditional health risk" has a greater impact on the first health risk information representing "unconditional health risk". Therefore, a larger weighting is set for the second health risk information to improve the sensitivity of the obtained third health risk information to the driver's actual health risks.

[0067] In this embodiment, a car equipped with an in-vehicle health monitoring system can achieve the same technical effects as an in-vehicle health monitoring system.

[0068] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. Furthermore, the descriptions of "upper," "lower," "left," and "right" used in this disclosure are only relative to the relative positional relationships of the components of this disclosure in the accompanying drawings. The singular forms "a," "an," and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. Moreover, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this embodiment specification is only for describing particular embodiments and is not intended to limit the invention. The term "and / or" as used in this embodiment includes any combination of one or more of the associated listed items.

[0069] It should be understood that although the terms first, second, third, etc., may be used to describe various elements in this disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element without departing from the scope of this disclosure, and similarly, a second element may also be referred to as a first element. The use of any and all instances or exemplary language (“e.g.,” “such as,” etc.) provided in this embodiment is intended only to better illustrate embodiments of the invention and, unless otherwise required, does not impose a limitation on the scope of the invention.

[0070] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).

[0071] Furthermore, the procedures described in this embodiment can be performed in any suitable order unless otherwise indicated by this embodiment or clearly contradicted by the context. The procedures (or variations and / or combinations thereof) described in this embodiment can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. A computer program includes multiple instructions executable by one or more processors.

[0072] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices, etc. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention of this embodiment includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps above in conjunction with a microprocessor or other data processor. When programmed according to the methods and techniques of the invention, the invention also includes the computer itself.

[0073] A computer program can be applied to input data to perform the functions of this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including a specific visual depiction of physical and tangible objects generated on the display.

[0074] The above are merely preferred embodiments of the present invention. The present invention is not limited to the above-described embodiments. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention, as long as they achieve the technical effects of the present invention by the same means, should be included within the scope of protection of the present invention. Within the scope of protection of the present invention, the technical solutions and / or implementation methods can have various modifications and variations.

Claims

1. A vehicle-mounted health monitoring system, characterized in that, The vehicle-mounted health monitoring system includes: An internal communication module; the internal communication module is used to communicate with the smart wearable device worn by the occupants of the vehicle, and to receive the time curve of the vital signs data detected by the smart wearable device on the occupants of the vehicle. A driving event detection module; the driving event detection module is used to detect the first driving event of the vehicle; the first driving event includes events in which the occupants of the vehicle operate the vehicle, as well as external events in the traffic environment in which the vehicle is located; The processing module is used to process the vital sign data time curve to obtain first health risk information, process the vital sign data time curve and the first driving event to obtain second health risk information, and process the first health risk information and the second health risk information to obtain third health risk information.

2. The vehicle-mounted health monitoring system according to claim 1, characterized in that, The process of processing the time curve of the vital signs data to obtain the first health risk information includes: The first curve segment is determined from the time curve of the vital signs data using the sliding window method; Perform feature recognition on the first curve segment to obtain first abnormal feature information; Based on the first abnormal feature information, the first health risk information is determined.

3. The vehicle-mounted health monitoring system according to claim 2, characterized in that, The first driving event of the detected vehicle includes: Whenever a driving event is detected, the event type of the driving event is detected, the driving event is recorded as a first driving event, and the detection time and event type of the first driving event are recorded.

4. The vehicle-mounted health monitoring system according to claim 3, characterized in that, The process of processing the time curve of the vital signs data and the first driving event to obtain the second health risk information includes: From all the first driving events, a plurality of second driving events are determined; the second driving events are the first driving events whose corresponding event type is the target type. Based on the detection time corresponding to each second driving event, the vital sign data time curve is divided into several second curve segments; Perform feature recognition on the last second curve segment to obtain the second abnormal feature information; The second health risk information is determined based on the second abnormal feature information.

5. The vehicle-mounted health monitoring system according to claim 4, characterized in that, The step of determining a plurality of second driving events from all the first driving events includes: Detect the real-time location information of the vehicle; Based on the real-time location information, determine the scene-specific target event; The event type of the specific target event in the scenario is determined as the target type; The first driving event, whose corresponding event type is the target type, is determined as the second driving event.

6. The vehicle-mounted health monitoring system according to claim 4, characterized in that, The step of determining a plurality of second driving events from all the first driving events includes: Iterate through all the event types corresponding to the first driving event; For any of the event types, obtain the periodicity of the time sequence of each of the first driving events corresponding to the event type arranged according to the detection time; Obtain the maximum value among all the stated periodicity levels; The event type corresponding to the maximum value is determined as the target type; The first driving event, whose corresponding event type is the target type, is determined as the second driving event.

7. The vehicle-mounted health monitoring system according to claim 4, characterized in that, The third health risk information is obtained by processing the first and second health risk information, including: Determine the weighting weights; The second health risk information is weighted according to the weighting weights and then superimposed on the first health risk information to obtain the third health risk information.

8. The vehicle-mounted health monitoring system according to claim 7, characterized in that, To determine the weighting, including: Obtain the overlap between the last second curve segment and the first curve segment; The weighting weights are determined based on the degree of overlap, in a positive correlation.

9. The vehicle-mounted health monitoring system according to any one of claims 1-8, characterized in that, The vehicle-mounted health monitoring system also includes: The smart wearable device; External communication module; the external communication module is used to send the third health risk information to the rescue terminal.

10. An automobile product, characterized in that, The automotive product includes the in-vehicle health monitoring system as described in any one of claims 1-9.

Images