Abnormal state alarm method, device, equipment and medium

Abstract

The invention relates to the technical field of alarm prompt, in particular to an abnormal state alarm method and device, equipment and a medium. By acquiring the current radar observation data of the current timestamp on the seat, the personnel state information on the seat can be captured in real time, and the empty seat mark of the seat is determined according to the current radar observation data, so that whether the seat is occupied or not can be distinguished, and excessive analysis of invalid data in the empty seat state is avoided. The current radar observation data is subjected to standardization processing in combination with an empty chair mark, and the availability mark of the standardized radar data is extracted, so that effective and reliable radar data can be screened out. The sedentariness level, the abnormal sitting posture level, the working pressure level and the heart health risk level are extracted and serve as the basis for outputting the alarm instruction, the audio module, the light module and the heating ventilation module are combined, so that generation of the alarm instruction is more scientific and targeted, and the abnormal state alarm effect of personnel is improved.

Description

Technical Field

[0001] This invention relates to the field of alarm notification technology, and in particular to an abnormal state alarm method, device, equipment and medium. Background Technology

[0002] With the fast pace of modern life and changing work styles, prolonged desk work or maintaining a fixed sitting posture has become the norm for many office workers, students, and certain professions. This sedentary behavior and poor posture not only easily lead to cervical spine problems but may also increase the risk of cardiovascular disease and negatively impact work efficiency and mental health. Traditional methods of human condition monitoring often rely on wearable devices such as smart bracelets and watches. These devices require users to wear them actively, which suffers from low comfort, poor compliance, and potential interference with users' daily activities, thus limiting the effectiveness of alarms. Therefore, improving the alarm effectiveness for abnormal human conditions during human condition monitoring is an urgent problem to be solved. Summary of the Invention

[0003] In view of this, embodiments of this application provide an abnormal state alarm method, device, equipment and medium to solve the problem of poor alarm effect for abnormal state of personnel during the monitoring of abnormal state of personnel.

[0004] Firstly, embodiments of this application provide an abnormal state alarm method, the abnormal state alarm method comprising: Obtain the current radar observation data with the current timestamp on the seat; determine the empty seat indicator based on the current radar observation data; perform standardization processing on the current radar observation data and the empty seat indicator to obtain standardized radar data; and extract the availability indicator of the standardized radar data. Based on the standardized radar data, the empty chair sign and the availability sign, the abnormal state of the person to be tested on the chair is detected, and the abnormality level of the abnormal state of the person to be tested is obtained. The abnormal state includes prolonged sitting, abnormal sitting posture, work stress and heart health. The abnormality level of the corresponding abnormal state includes prolonged sitting level, abnormal sitting posture level, work stress level and heart health risk level. Based on the level of prolonged sitting, the level of abnormal sitting posture, the level of work stress, and the level of heart health risk, an alarm command is output so that the alarm module outputs alarm information according to the alarm command.

[0005] Secondly, this application provides an abnormal state alarm device, which includes a bio-radar module, a main control module, and an alarm module, wherein the bio-radar module and the alarm module are respectively communicatively connected to the main control module; The bio-radar module is used to collect current radar observation data with the current timestamp on the seat and send the current radar observation data to the main control module; The main control module is used to execute any of the above-described abnormal state alarm methods and output alarm commands to the alarm module; The alarm module is used to output alarm information according to the alarm command.

[0006] Thirdly, embodiments of this application provide a computer device, the computer device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the abnormal state alarm method as described above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the abnormal state alarm method as described above.

[0008] The advantages of this application compared to the prior art are: By acquiring current radar observation data with the current timestamp on the seats, the real-time status information of the people on the seats can be captured. Determining the seat's vacancy status based on the current radar observation data helps distinguish whether a seat is occupied, avoiding over-analysis of invalid data in vacant seat states. Standardizing the current radar observation data by combining the vacancy status with usability indicators allows for the filtering of valid and reliable radar data. By extracting sedentary level, abnormal posture level, work stress level, and cardiac health risk level and using these as the basis for outputting alarm commands, and combining them with audio, lighting, and heating / ventilation modules, the generation of alarm commands becomes more scientific and targeted, thereby improving the effectiveness of alarms for abnormal personnel states. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating an abnormal state alarm method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an abnormal state alarm device provided in an embodiment of this application; Figure 3This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0013] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0014] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0015] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0016] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0017] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0018] It should be understood that the sequence number of each step in the following embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0019] To illustrate the technical solution of this application, specific embodiments are described below.

[0020] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an abnormal state alarm method provided in an embodiment of this application, which is applied to a seat. Figure 1 As shown, the abnormal state alarm method may include the following steps.

[0021] S101: Obtain the current radar observation data with the current timestamp on the seat, determine the seat's empty seat indicator based on the current radar observation data, standardize the current radar observation data based on the current radar observation data and the empty seat indicator to obtain standardized radar data, and extract the availability indicator of the standardized radar data.

[0022] In step S101, the current radar observation data with the current timestamp on the seat is the observation data collected by the bio-radar module installed on the seat. The bio-radar module includes a bio-radar device. An empty chair flag indicates whether there is someone on the seat; the empty chair flag includes a occupied flag and an unoccupied flag, with the occupied flag having a value of 1 and the unoccupied flag having a value of 0. An availability flag indicates the validity of the standardized radar data.

[0023] In this embodiment, a bio-radar module is installed on the rear side or inside of the seat back to collect current radar observation data on the seat. Specifically, the bio-radar module collects radar echo signals from the seat area in real time. This current radar observation data may include characteristic parameters such as the amplitude, phase, and frequency of the echo signal. Feature extraction is performed on the current radar observation data to determine whether there are feature components in the echo signal related to human physiological activities (such as breathing and heartbeat), or to determine whether the energy distribution of the echo signal conforms to a typical pattern when a human is present, thus determining whether there is a person on the seat. The typical pattern is a set of statistically regular features exhibited by the radar echo signal when a human is present. For example, when a person sits on the seat, the energy of the radar echo signal is mainly concentrated within a specific distance range and Doppler frequency range. This distance range corresponds to the spatial position of the torso and head of the person on the seat, while the Doppler frequency range is related to the minute displacements caused by weak physiological activities such as breathing and heartbeat, and typically includes specific frequency components and amplitude variation ranges. By comparing the extracted echo signal energy distribution characteristics with these pre-determined typical patterns, if the similarity exceeds a set threshold, the seat is determined to be occupied. Otherwise, it is determined to be unoccupied. When human-related features are detected, the empty chair flag is set to occupied (value 1). Conversely, when no human-related features are detected, or the echo signal characteristics match the empty chair status, the empty chair flag is set to unoccupied (value 0). Based on the current radar observation data and the empty chair flags, the current radar observation data is standardized to obtain standardized radar data.

[0024] Optionally, based on the current radar observation data and the empty chair marker, the current radar observation data is standardized to obtain standardized radar data, including: Based on the current radar observation data and the empty chair marker, determine the background radar observation data for the current timestamp; Extract effective observation data based on current radar observation data and background radar observation data; The effective observation data is smoothed to obtain standardized radar data.

[0025] In this embodiment, the bio-radar module adopts a preset update cycle. As a unified time base, the first n The timestamp of a reference moment is defined as: in, To initialize the start time, and to simultaneously meet the sampling requirements of macroscopic sitting posture perception and physiological micro-motion extraction, a low sampling rate link and a high sampling rate link are set up, with sampling intervals as follows: in, For the sampling interval of low sampling rate links, The sampling interval for high sampling rate links. The sampling frequency for low sampling rate links, This refers to the sampling frequency of the high-sampling-rate link. The low-sampling-rate link is used to output the radar observation sequences required for macroscopic posture perception, while the high-sampling-rate link is used to output the micro-motion observation sequences related to physiological signals. Both types of observations are indexed and aligned using a timestamp system.

[0026] Based on current radar observation data and the empty chair indicator, determine the background radar observation data for the current timestamp. Specifically, for the unoccupied state (i.e., when the empty chair indicator is 0), determine the calibration time window for the unoccupied state. A built-in static background template is represented as follows: in, Empty chair sign Based on current radar observation data, This represents a robust statistical calculation subprocess for taking the median of a sample set.

[0027] It should be noted that background radar observation data is only included in the unmanned state with a forgetting factor. The update process is performed while the background radar observation data remains unchanged in manned conditions, as shown below: Based on the current radar observation data and background radar observation data, effective observation data is extracted. Specifically, background filtering is applied to the current radar observation data based on the background radar observation data to obtain effective observation data. The calculation formula is as follows: in, To effectively observe data, Based on current radar observation data, Background radar observation data.

[0028] The effective observation data is processed to obtain standardized radar data. This involves updating the effective observation data at a preset sampling interval to obtain low-sampling-rate and high-sampling-rate observation data, represented as follows: in, For the first Low sampling rate observation data, For the first High sampling rate observation data, For the first The time corresponding to each low sampling point For the first The time corresponding to each high sampling point To initialize the start time, For the sampling interval of low sampling rate links, This refers to the sampling interval for high sampling rate links.

[0029] To suppress the impact of short-term noise or abnormal frames on subsequent sensing performance, the two types of observation data are smoothed, as shown below: in, For the first Smoothed observation data with a low sampling rate For the first High-sampling-rate smoothed observation data and This is the smoothing coefficient.

[0030] Based on the preset cache window length, a smoothed observation set within the window is constructed for the current timestamp, represented as: in, For a smooth set of observations within the window, For observation data obtained by indexing by timestamp, after smoothing at a low sampling rate. This is the observation data after smoothing at a high sampling rate. Sets the preset cache window length.

[0031] Standardized radar data generated at the current timestamp is represented as: in, The radar data is standardized, including timestamps and a smoothed set of observations within a window.

[0032] Extract availability indicators from standardized radar data. First, calculate the mean vector of the observation data smoothed at a low sampling rate within a preset window of the current timestamp. The calculation process for the mean vector of the observation data smoothed at a low sampling rate within the preset window of the current timestamp is expressed as follows: in, This is the mean vector of the observation data smoothed at a low sampling rate within a preset window of the current timestamp. This represents the set of observation data after smoothing at a low sampling rate.

[0033] The fluctuation measure of the observation data after smoothing at a low sampling rate is calculated using the following formula: in, It is a measure of discrete energy fluctuation, that is, a measure of the fluctuation of observation data after smoothing at a low sampling rate.

[0034] The same calculation process can also be used to obtain the fluctuation measure of observation data after high sampling rate smoothing. Based on the fluctuation metrics of observation data smoothed at low and high sampling rates, usability indicators for standardized radar data are extracted. Specifically, the usability indicators for standardized radar data are extracted by comparing the fluctuation metrics with a threshold. These indicators include usability indicators for attitude assessment input and physiological information assessment input. The usability indicators take values ​​of 1 and 0. A value of 1 indicates usable data, while a value of 0 indicates unusable data. This is represented as follows: in, As an availability indicator, Input availability flags for attitude assessment. The usability indicators for physiological information assessment inputs include both posture assessment input usability indicators and physiological information assessment input usability indicators. and For a threshold greater than zero, As an indicator function, when the requirements are met, The value is 1; otherwise, the value is 0. This means that both flags have only two states: "available (1)" and "unavailable (0)", resulting in a total of 4 possible input scenarios.

[0035] The standardized radar data and availability flags are combined and represented as follows: In this embodiment, by combining the original radar observation data with the empty chair indicator for standardized processing, the interference of invalid data in the empty chair state can be effectively eliminated. The extraction of the availability indicator provides a clear basis for the validity judgment of subsequent data processing, ensuring that only real and valid human body status-related data are included in the analysis process. This significantly improves the accuracy and reliability of subsequent detection of sedentary status, abnormal sitting posture, work stress status, and heart health status, and reduces false alarms or misjudgments caused by invalid data.

[0036] S102: Based on standardized radar data, empty chair signs, and availability signs, detect abnormal states of the person to be tested in the chair and obtain the abnormality level of the person to be tested. Abnormal states include prolonged sitting, abnormal sitting posture, work stress, and heart health. The corresponding abnormality levels are: prolonged sitting level, abnormal sitting posture level, work stress level, and heart health risk level.

[0037] In step S102, abnormal states represent a set of physiological or behavioral deviations of the person being tested from the normal range. Specifically, a sedentary state refers to a state where the cumulative duration of the person being tested maintaining a seated posture with activity levels below a set threshold exceeds a health warning value. An abnormal sitting posture refers to a state where various parts of the person being tested deviate from preset standard sitting posture parameters beyond the allowable range. Work stress status is used to determine whether the person being tested is experiencing excessive tension, anxiety, or other forms of stress. Cardiac health status assesses whether the person being tested is at risk of potential cardiac dysfunction.

[0038] In this embodiment, based on standardized radar data, empty chair signs, and availability signs, abnormal states of individuals on seats are detected to determine the abnormality level of their respective states. Specifically, for sedentary status detection, the cumulative duration of continuous sitting is calculated and compared with a health warning value to determine the sedentary level. For abnormal posture detection, a human posture model is constructed based on standardized radar data. Parameters such as spinal curvature angle and limb placement in the model are compared with preset standard posture parameters, and the abnormal posture level is determined based on the degree of deviation. For work stress detection, physiological indicators such as respiratory rate and heart rate variability, as well as subtle limb movement features, are extracted from standardized radar data. Specific algorithms are used to calculate these indicators and features to determine the work stress level of the individual, thereby determining the work stress level. Cardiac health status detection is based on cardiac-related physiological signals such as heart rate and cardiac impaction extracted from standardized radar data. By comparing these signals with the range of normal cardiac function parameters, the risk of potential cardiac dysfunction is assessed, resulting in a cardiac health risk level.

[0039] In this embodiment, the method can comprehensively and in real-time monitor the health and work status of people sitting in chairs through multi-dimensional abnormal state detection. By integrating multiple indicators such as sitting duration, posture, work pressure, and heart health, it achieves a comprehensive assessment of the person's status. Combining empty chair signs and availability signs for conditional judgment effectively improves the accuracy and reliability of detection.

[0040] Optionally, the sedentary level detection process includes: The effective cumulative count is calculated based on the empty chair sign and the availability sign; The duration of continuous sitting on the seat by the person to be tested is determined based on the effective cumulative markers. Based on the duration of continuous sitting, the individuals being tested are classified into different levels of sedentary behavior to obtain their sedentary behavior level.

[0041] In this embodiment, the effective cumulative flag is calculated based on the empty chair flag and the availability flag, and is represented as follows: in, For effective cumulative indicators, .

[0042] according to The duration of continuous sitting is calculated and expressed as: in, This represents the duration of continuous sitting at the previous timestamp. When sitting for a long time, press and hold Increasing, The duration of continuous sitting is set to zero. This avoids the accumulation of errors caused by leaving the seat or unavailable observation data.

[0043] The duration of continuous sitting is mapped to a sedentary level, which is divided into three levels. The longer the continuous sitting time, the higher the level. The calculation process is expressed as follows: in, This represents the sedentary level, with a value of 0, 1, or 2. As an indicator function, when the requirements are met, The value is 1; otherwise, the value is 0. and As a time threshold, Less than .

[0044] In this embodiment, by combining the empty chair sign and the availability sign to calculate the effective cumulative sign, the effective time period when the person to be tested is actually in the seat and the equipment is working normally can be accurately screened, avoiding the miscounting of sitting time caused by people leaving their seats or equipment failure.

[0045] Optionally, the detection process for abnormal sitting posture levels includes: Based on standardized radar data and availability indicators, a two-dimensional regular grid is constructed for the observation field of the back of the person to be detected; Based on a two-dimensional regular grid, the sitting posture of the person to be detected is extracted. The sitting posture includes the overall tilt of the back, the degree of back asymmetry, and the degree of back curvature. The abnormal sitting posture assessment index is calculated based on the overall tilt of the back, the degree of back asymmetry, and the degree of back curvature. The sitting posture abnormality assessment index is used to classify the sitting posture abnormality of the person being tested and obtain the sitting posture abnormality level.

[0046] In this embodiment, a two-dimensional regular grid of the observation field of the back of the person to be detected is constructed based on standardized radar data and availability flags. Specifically, the two-dimensional regular grid of the observation field of the back of the person to be detected is constructed when the availability flag is 1; that is, when both the attitude assessment input availability flag and the physiological information assessment input availability flag are 1, the two-dimensional regular grid of the observation field of the back of the person to be detected is constructed, as shown below: in, It is a two-dimensional regular grid. M , N These represent the number of grid cells in the horizontal and vertical directions of the back observation domain, respectively. Each grid cell constitutes a distance candidate set. This refers to the set of distances from all sampling points within each grid cell to the sensor, and the set of distances from all sampling points within each grid cell to the bio-radar module. Robust distances for each grid cell are statistically analyzed to construct a three-dimensional field matrix. Standardized radar data Represented as: in, The third field matrix The elements of the grid, This indicates the median statistical calculation process, used to reduce the impact of outlier frames or noise on 3D field distance estimation.

[0047] Smoothing the three-dimensional field matrix to reduce short-term noise interference is expressed as follows: in, For the smoothed data, The mean distance of the grid within the 3D field is calculated as a smoothing coefficient. , is represented as: in, for The Middle Each grid element corresponds to the smoothed data.

[0048] Based on a two-dimensional regular mesh, the sitting posture of the person being tested is extracted. The sitting posture includes the overall back tilt, back asymmetry, and back curvature. Specifically, the average gradient of the two-dimensional regular mesh in the same direction is calculated to obtain the overall back tilt. The overall back tilt reflects the magnitude of change in the three-dimensional field along the pitch direction and indicates the person's forward / backward tilt or support imbalance. The calculation formula is as follows: in, This represents the overall tilt of the back; the larger the value, the greater the overall tilt of the back.

[0049] The degree of back asymmetry is obtained by calculating the average distance difference between the left and right halves of a two-dimensional regular mesh, using the following formula: in, The value represents the degree of back asymmetry; the larger the value, the greater the degree of back asymmetry. This refers to the cell index of the left half of a two-dimensional regular mesh. This is the cell index for the right half of a two-dimensional regular grid.

[0050] The degree of back curvature is obtained by performing second-order difference calculations on a two-dimensional regular mesh, using the following formula: in, This represents the value indicating the degree of back curvature; the larger the value, the greater the degree of back curvature.

[0051] A posture abnormality assessment index is calculated based on the overall tilt, asymmetry, and curvature of the back. Specifically, abnormal indicators of overall back tilt, asymmetry, and curvature are determined based on these indicators. Furthermore, abnormal indicators of back asymmetry and curvature are used to determine the posture abnormality indicators, which are represented as follows: in, This is a sign of abnormal sitting posture. They are respectively , , , , , where are the threshold values ​​for the overall tilt of the back, the asymmetry of the back, and the curvature of the back, respectively. These are the abnormal signs of overall back tilt, back asymmetry, and back curvature, respectively. This is an indicator function.

[0052] The abnormal sitting posture markers are weighted to obtain the abnormal sitting posture assessment index, which is represented as follows: in, This is an assessment index for abnormal sitting posture. The weight value is greater than or equal to 0.

[0053] The sitting posture abnormality assessment index is used to classify the sitting posture of the personnel being tested into abnormalities, resulting in a sitting posture abnormality level. The abnormality level is divided into three grades, with a higher index indicating a higher level. The calculation process is as follows: in, This represents the level of abnormal sitting posture, with values ​​of 0, 1, and 2. A higher value indicates a more severe abnormal sitting posture. As an indicator function, when the requirements are met, The value is 1; otherwise, the value is 0. and This is the abnormal threshold. Greater than 0, Less than .

[0054] In this embodiment, a two-dimensional regular grid is constructed over the observation area of ​​the back of the person being tested, and sitting posture parameters such as the overall tilt of the back, the degree of back asymmetry, and the degree of back curvature are extracted from it. This allows for a comprehensive and detailed characterization of the sitting posture features of the person being tested. These parameters are then integrated to calculate a sitting posture anomaly assessment index, which is used to classify sitting posture anomalies, achieving a quantitative assessment and grading of the degree of sitting posture anomalies. This improves the accuracy and reliability of sitting posture extraction.

[0055] Optionally, the testing process for the working pressure level includes: Based on standardized radar data and availability indicators, the respiratory and cardiac characteristic sequences of the individuals to be tested are extracted. Based on the respiratory feature sequence, the respiratory rate and respiratory variability of the person being tested are extracted; based on the cardiac rhythm feature sequence, the heart rate and cardiac rhythm variability of the person being tested are extracted. The work stress levels of the personnel being tested are classified according to their respiratory rate, respiratory variability, heart rate and heart rate variability.

[0056] In this embodiment, when the availability flag is 1, the respiratory and cardiac feature sequences of the person to be tested are extracted. That is, when the physiological information assessment input availability flag is 1, the respiratory and cardiac feature sequences of the person to be tested are extracted based on standardized radar data. Within a preset statistical window, the standardized radar data undergoes bandpass filtering and detrending processing to enhance the low-frequency and high-frequency micro-motion components corresponding to respiration and cardiac contraction, respectively. Then, the respiratory component is processed using peak-valley detection or zero-crossing counting to obtain the respiratory cycle sequence, and the respiratory rate is calculated from the reciprocal of adjacent respiratory cycles. Simultaneously, respiratory variability is calculated based on the dispersion of the respiratory cycle or respiratory amplitude within the window. For the cardiac component, short-time energy surge detection, envelope peak detection, or template matching is used to locate the cardiac event moment, forming a cardiac interval sequence. The heart rate is obtained from the reciprocal of the cardiac interval, and cardiac variability is calculated based on the fluctuation of the cardiac interval within the window. This embodiment is not limited.

[0057] It should be noted that when using bandpass filtering, the frequency difference between respiratory and cardiac signals is utilized for separation and extraction. For example, a first bandpass filter for the respiratory signal is typically set between 0.1Hz and 0.5Hz to filter out noise and other interference components in the standardized radar data that are above or below this frequency range, thus obtaining a relatively pure respiratory feature sequence. Simultaneously, a second bandpass filter for the cardiac signal is set, typically between 0.8Hz and 3Hz, and similarly, the cardiac feature sequence is separated and extracted from the standardized radar data through filtering.

[0058] Based on the respiratory feature sequence, the respiratory rate and respiratory variability of the subject were extracted; based on the cardiac feature sequence, the heart rate and cardiac variability of the subject were extracted, and expressed as follows: in, Characterized by cardiopulmonary resuscitation. Respiratory rate, For respiratory variability, Heart rate, This refers to cardiac variability.

[0059] Work stress levels were determined by classifying the workload of the personnel being tested based on respiratory rate, respiratory variability, and heart rate and cardiac variability. To reduce the interference of individual differences and cumulative errors on work stress assessment, individual cardiopulmonary baseline characteristics were constructed and updated exponentially during periods of low work stress, as shown below: in, Baseline characteristics of individual cardiopulmonary function. To pre-define individual cardiopulmonary baseline characteristic update markers, K The smoothing factor for individual cardiopulmonary baseline characteristics is calculated based on the individual cardiopulmonary baseline characteristics, and the normalized deviation vector is expressed as: in, For the normalized deviation vector, , Used to avoid a denominator of zero.

[0060] Furthermore, a work stress assessment index is constructed by weighting the normalized deviation vectors to evaluate the positive contributions of increased respiratory rate and heart rate to work stress, as well as the positive contributions of decreased respiratory variability and cardiac variability to work stress, expressed as: in, As a stress assessment index, for The i Each component. The weighting coefficient is greater than or equal to zero.

[0061] The work stress level is calculated based on the work stress assessment index and is expressed as follows: in, This represents the work stress level, with values ​​of 0, 1, and 2. A higher value indicates greater work stress. For indicator functions, , which is the threshold for work stress level.

[0062] In this embodiment, respiratory and cardiac characteristic sequences are extracted, and physiological indicators such as respiratory rate, respiratory variability, heart rate, and cardiac variability are calculated to achieve a scientific classification of work stress levels. This fully utilizes the advantages of non-contact radar monitoring, eliminating the need for physical contact with the personnel being monitored. Physiological parameters can be acquired in real-time and continuously without interfering with their normal work, providing objective and accurate data support for work stress assessment. This avoids the discomfort and data acquisition interference that may arise from contact detection methods, improving the convenience and reliability of stress assessment.

[0063] Optionally, the process for assessing cardiac health risk levels includes: Time series of cardiac events were extracted based on standardized radar data and availability indicators. Based on the time series of cardiac events, the central value and dispersion of cardiac interval within the preset evaluation window are calculated; Based on the central value and dispersion of the cardiac interval, the first type of abnormal events and the second type of abnormal events within the preset evaluation window are statistically analyzed. The first type of abnormal events are abnormal events within the interval, and the second type of abnormal events are abnormal events between the intervals. Based on the first and second types of abnormal events, a risk assessment of the cardiac health of the individuals to be tested is conducted to obtain their cardiac health risk level.

[0064] Based on standardized radar data and availability indicators, cardiac event time series are extracted. Specifically, cardiac event time series are extracted when the availability indicator is 1, meaning that the cardiac event time series is extracted when the physiological information assessment input availability indicator is 1. A preset cardiac feature detection algorithm is used to identify the occurrence times of cardiac events in the standardized radar data. These times are then arranged chronologically to obtain the cardiac event time series. Furthermore, the cardiac interval sequence is calculated and represented as follows: in, The time interval between adjacent heartbeats For the first k The moment of the next cardiac event.

[0065] To achieve stable statistics on abnormal cardiac rhythm events, within a length of Evaluation window Internally construct a sample set of cardiac intervals And calculate the statistical sample size as .

[0066] Furthermore, the central value and dispersion of the intracardiac interval within the assessment window are calculated and expressed as follows: in, For the intercardiac center, For dispersion, This represents the statistical process of the median. is the normalization coefficient.

[0067] Based on the central value and dispersion of the heartbeat interval, the first type of abnormal events and the second type of abnormal events within the preset window are statistically analyzed. The first type of abnormal event is an abnormal event within the interval, which indicates that the heartbeat interval is significantly too short or too long. The second type of abnormal event is an abnormal event between intervals, which indicates abrupt changes in adjacent heartbeat intervals.

[0068] The first type of abnormal event is represented as: in, This is a Class 1 abnormal event. For indicator functions, When the value is 1, it is considered that a first-type abnormal event exists. When the value is 0, it is considered that there is no Type I exception. This represents the abnormal threshold within the interval.

[0069] The second type of abnormal event is represented as follows: in, This is a second type of abnormal event. For indicator functions, When the value is 1, it is considered that a second type of abnormal event exists. When the value is 0, it is considered that there is no second type of abnormal event. This represents the abnormal threshold during the interval.

[0070] Within the preset evaluation window, the proportions of the two types of abnormal events are statistically analyzed and represented as follows: in, The proportion of Category I abnormal events. The proportion of the second type of abnormal events. The number of cardiac events.

[0071] To reduce the interference of individual differences, a baseline feature of the proportion of abnormal cardiac events is constructed and updated under stable conditions, represented as: in, Baseline characteristics of the proportion of abnormal cardiac events. As a smoothing factor, This serves as the baseline feature update flag for the proportion of abnormal cardiac events.

[0072] The normalized deviation vector of cardiac abnormalities is calculated based on the baseline characteristics of the proportion of cardiac abnormalities, and is expressed as follows: in, This is the normalized deviation vector for abnormal cardiac events. This is used to avoid the denominator being zero.

[0073] A cardiac health risk assessment index is constructed based on a weighted combination of normalized deviation vectors of abnormal cardiac events, denoted as: in, As a heart health risk assessment index, and for The amount, and These are the weighting coefficients.

[0074] Based on the cardiac health risk assessment index, a risk assessment of the cardiac health of the individuals being tested is conducted to obtain their cardiac health risk level, which is expressed as: in, This represents the work stress level, with values ​​from 0 to 2. Higher values ​​indicate a greater risk to heart health. For indicator functions, Threshold for heart health risk level.

[0075] In this embodiment, by comprehensively analyzing the occurrence and severity of the first and second types of abnormal events, the potential abnormal patterns of cardiac activity in the person being tested can be captured more comprehensively and accurately, thereby providing a multi-dimensional quantitative basis for assessing the level of cardiac health risk and effectively improving the accuracy and reliability of risk assessment.

[0076] S103: Based on the level of prolonged sitting, abnormal sitting posture, work stress, and heart health risk, output alarm commands so that the alarm module can output alarm information according to the alarm commands.

[0077] In step S103, the alarm instruction is an instruction signal used to trigger the alarm module to perform a specific alarm operation. The alarm module can receive and parse the alarm instruction and perform the corresponding alarm operation according to the alarm instruction.

[0078] In this embodiment, the abnormal state alarm level of the person being tested is determined based on the level of sedentary behavior, abnormal posture, work stress, and heart health risk, as well as a preset mapping relationship of abnormal state alarm levels. An alarm command is generated according to the abnormal state alarm level and sent to the alarm module, causing the alarm module to output alarm information. Different abnormal state alarm levels correspond to different alarm messages. For example, abnormal state alarm levels include mild, moderate, and severe levels. When the abnormal state alarm level is mild, the alarm message can be output by flashing an indicator light at a specific frequency. When the abnormal state alarm level reaches severe, the alarm message can be output by a high-decibel buzzer and high-frequency flashing of the indicator light.

[0079] Optionally, alarm information can be output based on the level of sedentary behavior, the level of abnormal sitting posture, the level of work stress, and the level of heart health risk, including: Determine the maximum values ​​for the sedentary level, abnormal sitting posture level, work stress level, and heart health risk level, and determine the alarm intensity benchmark based on the maximum values; Based on the preset alarm priority order, determine the weight value of each abnormal state, and determine the target abnormal state based on the sedentary level, abnormal sitting posture level, work stress level, heart health risk level and the weight value of each abnormal state. Based on the alarm intensity benchmark and the target abnormal state, an alarm vector is constructed. Based on the alarm vector, an alarm command is output so that the alarm module can output alarm information according to the alarm command.

[0080] In this embodiment, the maximum values ​​of the sedentary level, abnormal sitting posture level, work stress level, and heart health risk level are determined. Based on these maximum values, an alarm intensity benchmark is determined. The alarm intensity benchmark represents the most prominent risk level among the four dimensions of sedentary level, abnormal sitting posture, work stress level, and heart health risk level for the person being tested, and is expressed as follows: in, This represents the maximum value of the sedentary level, abnormal sitting posture level, work stress level, and heart health risk level. The larger the value, the stronger the alarm.

[0081] Based on the preset alarm priority order, the weight value of each abnormal state is determined. Based on the sedentary level, abnormal sitting posture level, work stress level, heart health risk level and the weight value of each abnormal state, the target abnormal state is determined. The target state is represented as the alarm-dominated abnormal state.

[0082] The sedentary procrastination level, abnormal posture level, work stress level, and heart health risk level are weighted with their corresponding weight values ​​to obtain weighted sedentary procrastination level, weighted abnormal posture level, weighted work stress level, and weighted heart health risk level. The abnormal state corresponding to the maximum value among these weighted sedentary procrastination level, abnormal posture level, weighted work stress level, and weighted heart health risk level is identified as the target abnormal state. This is represented as: in, This serves as an indicator of the target's abnormal state. To assign a weight value to each abnormal state, the weight value for each abnormal state is determined according to a preset alarm priority order. For example, , The abnormality levels for each abnormal condition are: sedentary level, abnormal sitting posture level, work stress level, and heart health risk level.

[0083] Based on the alarm intensity benchmark and the target's abnormal state, an alarm vector is constructed. Based on the alarm vector, an alarm command is output, causing the alarm module to output alarm information according to the alarm command. The alarm module includes an audio unit, a lighting unit, and a heating and ventilation unit. The alarm vector represents the corresponding alarm intensity level, including the audio alarm intensity level, the lighting alarm intensity level, and the heating and ventilation alarm intensity level. This is represented as: in, For alarm vectors, The audio alarm intensity level for the current timestamp. The light alarm intensity level is the current timestamp. The current timestamp indicates the intensity level of the heating and ventilation alarm.

[0084] Each component is represented as follows: in, , This is the triggerable indicator for the corresponding unit, with values ​​of 1 and 0. If the value is 1, the corresponding unit needs to be triggered to output alarm information; if the value is 0, the corresponding unit does not need to be triggered to output alarm information. This is a hierarchical strategy mapping function for the corresponding unit, used to select an output level consistent with the intensity under different target anomaly states. This is the current timestamp. This is the previous timestamp.

[0085] Represented as: in, , This is the trigger timestamp of the previous output alarm message for the corresponding unit. This refers to the cooling time of the corresponding unit. This is an indicator function.

[0086] It should be noted that the hierarchical strategy mapping function must at least satisfy the following priority suppression constraints: When the heart health risk level is greater than or equal to 1, the output of the audio unit and the light unit is limited to a preset upper limit to avoid excessive alarm stimulation, and a voice prompt is given to increase rest or consult a doctor, while the output of the heating and ventilation unit is limited to the comfort range. When the work pressure level is greater than or equal to 1 and the heart health risk level is 0, the audio unit outputs a soothing alarm prompt or soft music, the light unit outputs a gentle mode with low-frequency changes, and the ventilation volume of the heating and ventilation unit is increased; when the abnormal sitting posture level is greater than or equal to 1 and the target abnormal state is not an abnormal sitting posture state, the audio unit outputs a sitting posture correction alarm, the light unit outputs a prompt mode with the intensity increasing with the alarm intensity benchmark, and the output of the heating and ventilation unit is synchronized to the preset comfort target; when the other state levels are 0, the audio unit and the light unit output a sedentary alarm mode with the intensity increasing with the alarm intensity benchmark, and the output of the heating and ventilation unit is synchronized to the preset comfort target. Other priority suppression constraints are also possible, and this embodiment does not limit them.

[0087] Based on the alarm vector, output the alarm command. This is represented as: in, For alarm commands, This is an alarm command for the audio unit, including alarm type, volume, and duration parameters. The alarm command for the lighting unit includes parameters for color, brightness, and flashing mode. The alarm command for the heating and ventilation unit includes the heating intensity, ventilation intensity, and target temperature and humidity range. This is a function for generating multimodal linkage instructions. This serves as an indicator of the target's abnormal state. This is the alarm vector.

[0088] The alarm command is sent to each unit in the alarm module, so that each unit outputs alarm information according to the alarm command.

[0089] It should be noted that, based on the level of prolonged sitting, abnormal sitting posture, work stress, and heart health risk, control commands can also be output to adjust the volume, playback mode, and duration of the audio unit in the alarm module, the brightness, color, and dynamic mode of the lighting unit, and the temperature and airflow intensity of the user contact area of ​​the heating and ventilation unit.

[0090] By acquiring current radar observation data with the current timestamp on the seats, the real-time status information of the people on the seats can be captured. Determining the seat's vacancy status based on the current radar observation data helps distinguish whether a seat is occupied, avoiding over-analysis of invalid data in vacant seat states. Standardizing the current radar observation data by combining the vacancy status with usability indicators allows for the filtering of valid and reliable radar data. By extracting sedentary level, abnormal posture level, work stress level, and cardiac health risk level and using these as the basis for outputting alarm commands, and combining them with audio, lighting, and heating / ventilation modules, the generation of alarm commands becomes more scientific and targeted, thereby improving the effectiveness of alarms for abnormal personnel states.

[0091] Please see Figure 2 , Figure 2 This is a schematic diagram of an abnormal state alarm device provided in one embodiment of this application. Please refer to the following for details. Figure 1 as well as Figure 1 The relevant descriptions in the corresponding embodiments are provided. This abnormal state alarm device is applied to a seat; for ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 2 The abnormal state alarm device includes a bio-radar module, a main control module, an alarm module, and a power supply module. The bio-radar module and the alarm module are respectively connected to the main control module for communication.

[0092] The bio-radar module is used to collect the current radar observation data with the current timestamp on the seat and send the current radar observation data to the main control module; The main control module is used to execute abnormal state alarm methods and output alarm commands to the alarm module; The alarm module is used to output alarm information according to alarm commands. The alarm module includes an audio unit, a lighting unit, and a heating and ventilation unit. The power module is used to provide operating power to the bio-radar module, the main control module and the alarm module.

[0093] It should be noted that this abnormal status alarm device is applied to the seat. The bio-radar module, located on the back or inside of the seat back, is used for non-contact radar observation of the back area of ​​the person being tested, acquiring radar observation data for work status monitoring. The bio-radar module can output standardized radar data after standardization, as well as empty chair and availability indicators, to support subsequent abnormal monitoring of sedentary status, sitting posture, work stress, and cardiac health risks.

[0094] The pre-defined data interface transmits the data to the main control module. Upon receiving the current radar observation data, the main control module first performs a preliminary judgment on the validity of the data, such as checking whether the empty chair indicator is not empty and whether the availability indicator indicates that the data is available. If the data is valid, the main control module will perform multi-dimensional analysis and processing of the current radar observation data based on the built-in abnormal status alarm method and the current timestamp information to identify whether the person in the seat is in an abnormal state such as prolonged sitting, poor posture, excessive work pressure, or heart health risks.

[0095] The main control module is electrically or communicatively connected to the bio-radar module. It is used to acquire current radar observation data with the current timestamp on the seat. Based on this data, it determines the seat's vacancy status. The current radar observation data and vacancy status are then standardized to obtain standardized radar data, and an availability flag is extracted. Based on the standardized radar data, vacancy status, and availability flag, the module detects abnormal states of the person being tested on the seat, determining the abnormality level of each state. Abnormal states include prolonged sitting, abnormal posture, work stress, and cardiac health. Corresponding abnormality levels are prolonged sitting level, abnormal posture level, work stress level, and cardiac health risk level. Based on these levels, alarm commands are output.

[0096] The alarm module includes an audio unit, a lighting unit, and a heating and ventilation unit. The main control module sends alarm commands to each unit in the alarm module, causing each unit to output alarm information according to the alarm commands. The audio unit is located on both sides of the seat headrest and is used to output voice alarms, prompts for prolonged sitting and posture correction, pressure relief guidance audio prompts, and soft music, as well as adjust the volume, playback mode, and duration, according to the alarm commands from the main control module.

[0097] The heating and ventilation unit is located in the seat cushion area and is used to adjust the local microenvironment of the seat according to the alarm command of the main control module, including heating and ventilation functions, so as to realize graded control of the temperature and air flow intensity of the user contact area, thereby improving comfort and cooperating with alarm intervention for abnormal working conditions.

[0098] The lighting unit is located around the seat and is used to output lighting alarms and ambient cues according to the alarm commands of the main control module. It also supports the adjustment of brightness, color and dynamic mode to achieve linkage alarms and graded cues with audio and temperature and humidity control.

[0099] The power module is used to provide operating power to the bio-radar module, the main control module and the alarm module. That is, the power module provides operating power to the bio-radar module, the main control module, the audio unit, the heating and ventilation unit and the lighting unit, and performs voltage regulation, overcurrent and overtemperature protection.

[0100] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0101] Figure 3 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. For example... Figure 3 As shown, the computer device of this embodiment includes: at least one processor ( Figure 3 Only one is shown in the diagram), a memory, and a computer program stored in the memory and executable on at least one processor, wherein the processor executes the computer program to implement the steps in any of the above-described abnormal state alarm method embodiments.

[0102] This computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 3 The examples of computer devices are merely examples and do not constitute a limitation on computer devices. Computer devices may include more or fewer components than shown in the illustration, or combinations of certain components, or different components, such as network interfaces, displays, and input devices.

[0103] The processor referred to can be a CPU, but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0104] Memory includes readable storage media, internal memory, etc., wherein internal memory can be the RAM of a computer device, providing an environment for the operation of the operating system and computer-readable instructions stored in the readable storage media. The readable storage media can be the hard drive of a computer device, or in other embodiments, it can be an external storage device of the computer device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, memory can include both internal storage units and external storage devices of the computer device. Memory is used to store the operating system, applications, bootloader, data, and other programs, such as program code for computer programs. Memory can also be used to temporarily store data that has been output or will be output.

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code, a recording medium, a computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0106] The implementation of all or part of the processes in the methods of the above embodiments can also be accomplished by a computer program product. When the computer program product is run on a computer device, it enables the computer device to execute the steps in the above method embodiments.

[0107] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0108] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0109] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An abnormal state alarm method, characterized in that, The abnormal status alarm method includes: Obtain the current radar observation data with the current timestamp on the seat; determine the empty seat indicator based on the current radar observation data; perform standardization processing on the current radar observation data and the empty seat indicator to obtain standardized radar data; and extract the availability indicator of the standardized radar data. Based on the standardized radar data, the empty chair sign and the availability sign, the abnormal state of the person to be tested on the chair is detected, and the abnormality level of the abnormal state of the person to be tested is obtained. The abnormal state includes prolonged sitting, abnormal sitting posture, work stress and heart health. The abnormality level of the corresponding abnormal state includes prolonged sitting level, abnormal sitting posture level, work stress level and heart health risk level. Based on the level of prolonged sitting, the level of abnormal sitting posture, the level of work stress, and the level of heart health risk, an alarm command is output so that the alarm module can output alarm information according to the alarm command.

2. The abnormal state alarm method as described in claim 1, characterized in that, The step of standardizing the current radar observation data based on the current radar observation data and the empty chair marker to obtain standardized radar data includes: Based on the current radar observation data and the empty chair marker, determine the background radar observation data for the current timestamp; Based on the current radar observation data and the background radar observation data, extract the effective observation data; The effective observation data is smoothed to obtain standardized radar data.

3. The abnormal state alarm method as described in claim 1, characterized in that, The process for detecting the sedentary level includes: The effective cumulative flag is calculated based on the empty chair flag and the availability flag; Based on the effective cumulative marker, the duration of continuous sitting of the person to be tested on the seat is determined; Based on the duration of continuous sitting, the individuals being tested on the seats are classified into different levels of sitting ability to obtain their sitting ability level.

4. The abnormal state alarm method as described in claim 1, characterized in that, The detection process for the abnormal sitting posture level includes: Based on the standardized radar data and the availability flag, a two-dimensional regular grid is constructed for the observation field of the back of the person to be detected; Based on the two-dimensional regular grid, the sitting posture of the person to be detected is extracted, including the overall tilt of the back, the degree of back asymmetry, and the degree of back curvature. The abnormal sitting posture assessment index is calculated based on the overall tilt of the back, the degree of asymmetry of the back, and the degree of curvature of the back. The sitting posture abnormality assessment index is used to classify the sitting posture abnormality of the person being tested, and the sitting posture abnormality level is obtained.

5. The abnormal state alarm method as described in claim 1, characterized in that, The detection process for the working pressure level includes: Based on the standardized radar data and the availability flag, extract the respiratory feature sequence and heartbeat feature sequence of the person to be tested; Based on the respiratory feature sequence, the respiratory rate and respiratory variability of the person to be tested are extracted; based on the cardiac rhythm feature sequence, the heart rate and cardiac rhythm variability of the person to be tested are extracted. The work stress of the personnel under test is classified into levels based on the respiratory rate, respiratory variability, heart rate and heart rate variability, thus obtaining the work stress level.

6. The abnormal state alarm method as described in claim 1, characterized in that, The process for assessing the heart health risk level includes: Based on the standardized radar data and the availability flag, extract the time series of cardiac events; Based on the cardiac event time series, the cardiac interval center value and dispersion within the preset evaluation window are calculated; Based on the cardiac interval center value and the dispersion, the first type of abnormal events and the second type of abnormal events within the preset evaluation window are statistically analyzed. The first type of abnormal events are abnormal events within the interval, and the second type of abnormal events are abnormal events between the intervals. Based on the first type of abnormal event and the second type of abnormal event, a risk assessment of the heart health of the person to be tested is performed to obtain the heart health risk level of the person to be tested.

7. The abnormal state alarm method as described in claim 1, characterized in that, The alarm command is output based on the sedentary level, the abnormal sitting posture level, the work stress level, and the heart health risk level, including: Determine the maximum value of the sedentary level, the abnormal sitting posture level, the work stress level, and the heart health risk level, and determine the alarm intensity benchmark based on the maximum value; Based on the preset alarm priority order, the weight value of each abnormal state is determined, and the target abnormal state is determined based on the sedentary level, the abnormal sitting posture level, the work pressure level, the heart health risk level and the weight value of each abnormal state. Based on the alarm intensity benchmark and the target abnormal state, an alarm vector is constructed, and an alarm command is output based on the alarm vector, so that the alarm module outputs alarm information according to the alarm command.

8. An abnormal state alarm device, characterized in that, The abnormal state alarm device includes a bio-radar module, a main control module, an alarm module, and a power supply module. The bio-radar module and the alarm module are respectively communicatively connected to the main control module. The bio-radar module is used to collect current radar observation data with the current timestamp on the seat and send the current radar observation data to the main control module; The main control module is used to execute the abnormal state alarm method according to any one of claims 1 to 7, and output alarm instructions to the alarm module; The alarm module is used to output alarm information according to the alarm command. The alarm module includes an audio unit, a lighting unit, and a heating and ventilation unit. The power module is used to provide operating power to the bio-radar module, the main control module and the alarm module.

9. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the abnormal state alarm method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the abnormal state alarm method as described in any one of claims 1 to 7.

Images