Rhythm state detection method, electronic device and program product

Abstract

The invention provides a rhythm state detection method, electronic equipment and a program product, and relates to the technical field of intelligent detection. The method comprises the following steps: acquiring multi-modal sign data representing the body pressure state of an operator on duty; performing feature extraction on the multi-modal sign data to obtain feature data corresponding to each piece of sign data in the multi-modal sign data; and according to the feature data, determining a fatigue level of the operator on duty as a rhythm state detection result of the operator on duty. Therefore, the problem that the accuracy of the body rhythm state detection result of the operator on duty is insufficient due to the single physical sign data type in the traditional body rhythm state detection mode of the operator on duty can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent detection technology, and more specifically, to a rhythm state detection method, electronic device, and program product. Background Technology

[0002] In daily work, especially in production operations and medical rescue, staff often need to work in shifts day and night due to work requirements (such as the need for work efficiency and the monitoring of patient safety).

[0003] To monitor the physical condition of staff working day and night, and to adjust their shifts promptly based on the physical stress levels (usually reflected in their circadian rhythm) of night shift workers (hereinafter referred to as on-duty personnel), thus providing them with sufficient rest time and preventing excessive physical strain from long night shifts that could negatively impact their health, current technologies often assess the physical condition of on-duty personnel using single data points, such as sleep duration and body temperature. However, in practical applications, single vital sign data (i.e., data representing the physical condition of on-duty personnel) often fails to accurately reflect their physical condition due to the accuracy, randomness, and variations in the vital sign performance of different on-duty personnel. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a rhythm state detection method, electronic device and program product, which can improve the problem that the traditional method of detecting the body rhythm state of on-duty personnel has insufficient accuracy due to the single data type of vital signs.

[0005] To achieve the above technical objectives, the technical solution adopted in this application is as follows:

[0006] In a first aspect, embodiments of this application provide a rhythm state detection method, the method comprising:

[0007] Acquire multimodal vital signs data representing the physical stress state of on-duty personnel;

[0008] Feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data in the multimodal vital sign data;

[0009] Based on the characteristic data, the fatigue level of the on-duty personnel is determined, which serves as the result of the on-duty personnel's rhythm state detection.

[0010] In conjunction with the first aspect, in one optional implementation, the multimodal vital signs data includes the on-duty personnel's body temperature data, heart rate data, ambient light data, and cortisol data;

[0011] Acquire multimodal vital signs data characterizing the physical stress state of on-duty personnel, including:

[0012] The body temperature of the on-duty personnel is collected at a first preset frequency during a first preset time period and used as the body temperature data;

[0013] The heart rate of the on-duty personnel is collected at a second preset frequency during a second preset time period, and used as the heart rate data.

[0014] The light intensity of the on-duty personnel during the third preset time period is collected at a third preset frequency and used as the ambient light data;

[0015] The cortisol concentration of the on-duty personnel during the fourth preset time period is collected at a fourth preset frequency and used as the cortisol data.

[0016] In conjunction with the first aspect, in one optional implementation, feature extraction is performed on the multimodal vital sign data to obtain feature data corresponding to each vital sign data item in the multimodal vital sign data, including:

[0017] Feature extraction is performed on the body temperature data to obtain the phase offset and amplitude deviation between the body temperature data of the duty personnel during night duty and the reference body temperature data, as well as the rate of decrease of body temperature of the duty personnel during the fifth preset period during the night duty, which are used as the body temperature feature data corresponding to the body temperature data.

[0018] Feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data;

[0019] Based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain the light feature data corresponding to the ambient light data;

[0020] Feature extraction is performed on the cortisol data to obtain the rhythm fluctuations and cumulative deviations corresponding to the cortisol data, which are used as the cortisol feature data corresponding to the cortisol data.

[0021] In conjunction with the first aspect, in an optional implementation, feature extraction is performed on the body temperature data to obtain the phase offset and amplitude deviation between the body temperature data of the on-duty personnel during night shifts and reference body temperature data, as well as the rate of temperature decrease of the on-duty personnel during a fifth preset time period during night shifts, which are used as the body temperature feature data corresponding to the body temperature data, including:

[0022] Temperature curves are fitted to the body temperature data and the reference body temperature data respectively to obtain the night shift curve corresponding to the body temperature data and the baseline curve corresponding to the reference body temperature data.

[0023] The phase offset and the amplitude deviation are determined based on the baseline curve and the night shift curve.

[0024] The rate of decrease in body temperature is determined based on the body temperature data.

[0025] In conjunction with the first aspect, in one optional implementation, feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data, including:

[0026] Based on the heart rate data, determine the time-domain features in the heart rate variability feature data;

[0027] The power spectrum was obtained by performing a Fourier transform on the heart rate data.

[0028] In the power spectrum, frequency bands below a preset frequency are designated as low-frequency bands, and frequency bands above or equal to the preset frequency are designated as high-frequency bands. Based on the power corresponding to the low-frequency bands and the high-frequency bands, the frequency domain features in the heart rate variability feature data are determined.

[0029] In conjunction with the first aspect, in one optional implementation, based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain light feature data corresponding to the ambient light data, including:

[0030] Based on the body temperature data and the ambient light data, determine the light sensitivity characteristics in the light characteristic data that characterize the degree of influence of light intensity on body temperature.

[0031] In conjunction with the first aspect, in an optional implementation, feature extraction is performed on the cortisol data to obtain the rhythmic fluctuations and cumulative deviations corresponding to the cortisol data, which serve as the cortisol feature data corresponding to the cortisol data, including:

[0032] Based on the cortisol data, the difference between the cortisol concentrations corresponding to the start and end times of the night shift for the on-duty personnel is determined as the circadian rhythm fluctuation;

[0033] Based on the cortisol data, the sum of the differences between the cortisol concentration of the on-duty personnel at the start time of their night shift and the preset reference concentration within the sixth preset time period is determined as the cumulative deviation.

[0034] In conjunction with the first aspect, in one optional implementation, determining the fatigue level of the on-duty personnel based on the characteristic data, as the result of the on-duty personnel's rhythm state detection, includes:

[0035] When the feature data is within a preset range, the feature score corresponding to the feature data is set to the first preset score;

[0036] When the feature data is not in the preset range, the feature score corresponding to the feature data is set to the second preset score;

[0037] Summing all the first preset scores and the second preset scores yields the comprehensive score corresponding to the feature data;

[0038] Based on the comprehensive score, the fatigue level of the on-duty personnel is determined as the result of the rhythm state detection.

[0039] Secondly, embodiments of this application also provide an electronic device, which includes a processor and a memory coupled to each other. The memory stores a computer program, and when the computer program is executed by the processor, the electronic device performs the above-described method.

[0040] Thirdly, embodiments of this application also provide a computer program product, including a computer program that implements the above-described method when executed by a processor.

[0041] The invention employing the above technical solution has the following advantages:

[0042] The technical solution provided in this application first acquires multimodal vital sign data characterizing the physical stress state of on-duty personnel. Then, feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data item. Finally, based on the feature data, the fatigue level of the on-duty personnel is determined as the result of their circadian rhythm detection. Thus, by using multimodal vital sign data as a reference indicator characterizing the physical stress / circadian rhythm state of on-duty personnel, and determining their fatigue level based on this reference indicator, the accuracy of judging the physical stress / circadian rhythm state of on-duty personnel is improved. This addresses the problem of insufficient accuracy in traditional methods of detecting the physical circadian rhythm state of on-duty personnel due to the single data type of vital signs. Attached Figure Description

[0043] This application can be further illustrated by the non-limiting embodiments given in the accompanying drawings. It should be understood that the following drawings only illustrate some embodiments of this application and should not be considered as limiting the scope. For those skilled in the art, other related drawings can be obtained from these drawings without any inventive effort.

[0044] Figure 1 A structural block diagram of an electronic device provided in an embodiment of this application.

[0045] Figure 2 This is a flowchart illustrating the rhythm state detection method provided in an embodiment of this application.

[0046] Icons: 100 - Electronic device; 101 - Processor; 102 - Memory. Detailed Implementation

[0047] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts are referred to by the same reference numerals in the drawings or description. Implementations not shown or described in the drawings are forms known to those skilled in the art. In the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0048] Please refer to Figure 1 This application provides an electronic device 100 that may include a processor 101 and a memory 102. The memory 102 stores a computer program, which, when executed by the processor 101, enables the electronic device 100 to perform the corresponding steps in the following rhythm state detection method.

[0049] In this embodiment, the processor 101 can be an integrated circuit chip with signal processing capabilities. The processor 101 can be a general-purpose processor. For example, the processor 101 can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0050] The memory 102 can be, but is not limited to, random access memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, etc. In this embodiment, the memory 102 can be used to store multimodal vital sign data, feature data, comprehensive scores, fatigue levels, rhythm state detection results, etc. Of course, the memory 102 can also be used to store programs, which the processor 101 executes after receiving an execution instruction.

[0051] In this embodiment, the electronic device 100 can be a personal computer, laptop computer, etc. It is used to acquire multimodal vital sign data characterizing the physical stress state of on-duty personnel. Then, feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data item. Finally, based on the feature data, the fatigue level of the on-duty personnel is determined as the result of the on-duty personnel's rhythm state detection.

[0052] Understandable Figure 1 The electronic device 100 shown is only a schematic diagram; the electronic device 100 may also include components that are more... Figure 1 More components are shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0053] In practical applications, to facilitate the implementation of the following rhythm state detection method, the electronic device 100 may also include a wrist temperature sensor, a heart rate sensor, and a light sensor that are communicatively connected to the processor 101 and the memory 102 (in practical applications, these can be integrated into wearable devices such as smartwatches and wristbands that carry the aforementioned sensors). The electronic device 100 also includes a flexible patch for cortisol concentration detection (in practical applications, this can also be manifested as a sweat detection flexible patch with the function of detecting the components of sweat excreted from the body surface of on-duty personnel).

[0054] Please refer to Figure 2 This application also provides a rhythm state detection method, which can be applied to the above-mentioned electronic device 100, and the electronic device 100 executes or implements the steps of the method. The rhythm state detection method may include the following steps:

[0055] Step 210: Obtain multimodal vital sign data representing the physical stress state of on-duty personnel;

[0056] Step 220: Extract features from the multimodal vital signs data to obtain feature data corresponding to each vital sign data in the multimodal vital signs data;

[0057] Step 230: Determine the fatigue level of the on-duty personnel based on the feature data, and use it as the result of the on-duty personnel's rhythm state detection.

[0058] In the above implementation method, multimodal vital sign data representing the physical stress state of on-duty personnel are first acquired. Then, feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data item. Finally, based on the feature data, the fatigue level of the on-duty personnel is determined as the result of their circadian rhythm status detection. Thus, using multimodal vital sign data as a reference indicator representing the physical stress state / circadian rhythm status of on-duty personnel can improve the accuracy of judging their physical stress state / circadian rhythm status and address the problem of insufficient accuracy in traditional methods of detecting the physical circadian rhythm status of on-duty personnel due to the single data type of vital signs.

[0059] The steps of the rhythm state detection method will be explained in detail below:

[0060] In step 210, the multimodal vital signs data may include the on-duty personnel's body temperature data, heart rate data, ambient light data, and cortisol data;

[0061] Acquiring multimodal vital sign data characterizing the physical stress state of on-duty personnel may include:

[0062] The body temperature of the on-duty personnel is collected at a first preset frequency during a first preset time period and used as the body temperature data;

[0063] The heart rate of the on-duty personnel is collected at a second preset frequency during a second preset time period, and used as the heart rate data.

[0064] The light intensity of the on-duty personnel during the third preset time period is collected at a third preset frequency and used as the ambient light data;

[0065] The cortisol concentration of the on-duty personnel during the fourth preset time period is collected at a fourth preset frequency and used as the cortisol data.

[0066] In this embodiment, the first preset frequency, second preset frequency, third preset frequency, and fourth preset frequency can be flexibly set according to user needs, such as collecting data once every 3 minutes, once every 5 minutes, once every 10 minutes, etc. The first preset time period, second preset time period, third preset time period, and fourth preset time can be flexibly set according to user needs, such as representing the working hours of the duty personnel during the day shift and representing the working hours of the duty personnel during the night shift. Each preset time period can include at least one sub-time period. For example, when the first preset time period is the working hours of the duty personnel during the night shift, the first preset time period can be from 22:00 to 6:00 the next day. This time period can include one or more sub-time periods (which can be divided equally according to the number of time periods).

[0067] In practical applications, the aforementioned body temperature data can be collected every 5 minutes, separately for night shift and day shift personnel, serving as body temperature data and reference body temperature data (day shift personnel typically experience lower stress and are considered healthy, used for comparative analysis with night shift personnel); the aforementioned heart rate data can be collected every minute, collecting the temporal data of the instantaneous heart rate of personnel during the night shift, serving as heart rate data; the ambient light intensity of the environment in which personnel are located during the night shift is collected every 10 minutes, serving as ambient light data; and the cortisol concentration of personnel during the night shift is collected every 30 minutes, serving as cortisol data.

[0068] In step 220, feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data in the multimodal vital sign data, which may include:

[0069] Feature extraction is performed on the body temperature data to obtain the phase offset and amplitude deviation between the body temperature data of the duty personnel during night duty and the reference body temperature data, as well as the rate of decrease of body temperature of the duty personnel during the fifth preset period during the night duty, which are used as the body temperature feature data corresponding to the body temperature data.

[0070] Feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data;

[0071] Based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain the light feature data corresponding to the ambient light data;

[0072] Feature extraction is performed on the cortisol data to obtain the rhythm fluctuations and cumulative deviations corresponding to the cortisol data, which are used as the cortisol feature data corresponding to the cortisol data.

[0073] In this embodiment, feature extraction is performed on the body temperature data to obtain the phase offset and amplitude deviation between the body temperature data of the staff member on night duty and the reference body temperature data, as well as the rate of temperature decrease of the staff member during the fifth preset time period during the night duty. These, as the body temperature feature data corresponding to the body temperature data, may include:

[0074] Temperature curves are fitted to the body temperature data and the reference body temperature data respectively to obtain the night shift curve corresponding to the body temperature data and the baseline curve corresponding to the reference body temperature data.

[0075] The phase offset and the amplitude deviation are determined based on the baseline curve and the night shift curve.

[0076] The rate of decrease in body temperature is determined based on the body temperature data.

[0077] In this embodiment, to ensure the stability of subsequent feature extraction, noise reduction of the body temperature data and the reference body temperature data can be performed using a moving average filter before feature extraction from the body temperature data:

[0078] (1)

[0079] In the formula, Indicates the staff on duty exist The denoised body temperature data corresponding to each time point (the reference body temperature data and the actual body temperature data are identical in format, acquisition method, and source; the only difference is the acquisition time. Therefore, for ease of description, the reference body temperature data is considered part of the actual body temperature data here). 12 (i.e., subscripts 0 to 11) represents the sliding window size, corresponding to 60 minutes (i.e., an acquisition frequency of 5 minutes × 12), and 0.083 represents the acquisition interval. Thus, through moving average filtering, interference from short-term activities is eliminated.

[0080] After filtering and denoising, this embodiment performs curve fitting on the denoised body temperature data and the reference body temperature data to obtain the baseline curve and the night shift curve:

[0081] Baseline curve:

[0082] Night shift curve:

[0083] In the formula, / This represents the baseline body temperature for the day / night shift (i.e., the average body temperature over 24 hours). , This represents the potential amplitude during the day / night shift, characterizing the maximum difference between the peak body temperature and the baseline body temperature during the day / night shift. , This indicates the peak phase point of the day / night shift (e.g., the peak body temperature during the day shift is at 1 PM). / This indicates a preset phase correction term (used to compensate for errors). , This represents the day / night shift time variable.

[0084] Then, based on the peak phase points of the baseline curve and the night shift curve, the phase offset is determined:

[0085] (2)

[0086] In the formula, Indicates phase offset. This indicates the theoretical phase shift of a reversed work-rest schedule. For example, if the peak body temperature during the day shift is at 2 PM, the theoretical peak body temperature during the night shift should be at 4 PM (i.e., 2 AM the next day).

[0087] Then, based on the potential amplitudes of the baseline curve and the night shift curve, the amplitude deviation is determined:

[0088] (3)

[0089] In the formula, This indicates amplitude deviation.

[0090] Then, based on the body temperature data, determine the rate of temperature decrease:

[0091] (4)

[0092] In the formula, Indicates the rate of decrease in body temperature. , express , Body temperature data at any given time.

[0093] In this embodiment, feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data, which may include:

[0094] Based on the heart rate data, determine the time-domain features in the heart rate variability feature data;

[0095] The power spectrum was obtained by performing a Fourier transform on the heart rate data.

[0096] In the power spectrum, frequency bands below a preset frequency are designated as low-frequency bands, and frequency bands above or equal to the preset frequency are designated as high-frequency bands. Based on the power corresponding to the low-frequency bands and the high-frequency bands, the frequency domain features in the heart rate variability feature data are determined.

[0097] In this embodiment, the heart rate interval is first determined based on heart rate data:

[0098] (5)

[0099] In the formula, Indicates the interval between heartbeats. Indicates the staff on duty exist Instantaneous heart rate at any given moment This indicates the heartbeat sequence number.

[0100] Then, based on the heartbeat interval, the time-domain features are determined:

[0101] (6)

[0102] (7)

[0103] In the formula, , These represent the standard deviation of the heartbeat interval and the root mean square of the difference between adjacent heartbeat intervals, respectively, in the time domain characteristics. Indicates the staff on duty Total heart rate during the night shift This represents the average heart rate interval.

[0104] Then, a Fourier transform is performed on the heart rate data to obtain the power spectrum. Frequency bands below a preset frequency are designated as low-frequency bands (representing the sympathetic nervous system), and frequency bands above the preset frequency are designated as high-frequency bands (representing the vagus nerve). The preset frequency can be flexibly set according to actual conditions; in this embodiment, the preset frequency can be 0.15Hz. In practical applications, the low-frequency and high-frequency bands essentially represent a frequency range, typically with upper and lower limits. In this embodiment, the low-frequency band is typically (0.04-0.15Hz), and the high-frequency band is typically (0.15-0.4Hz).

[0105] Then, based on the power spectrum, the power corresponding to the low-frequency and high-frequency bands is calculated separately (by integrating and summing the power corresponding to each frequency category in the low / high-frequency bands). Then, based on the power corresponding to the low-frequency and high-frequency bands respectively, the frequency domain features in the heart rate variability characteristic data are determined:

[0106] (8)

[0107] In the formula, Represents frequency domain characteristics, Indicates low-frequency power. This indicates high-frequency power.

[0108] In this embodiment, based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain the light feature data corresponding to the ambient light data, which may include:

[0109] Based on the body temperature data and the ambient light data, determine the light sensitivity characteristics in the light characteristic data that characterize the degree of influence of light intensity on body temperature.

[0110] In this embodiment, light sensitivity characteristics are determined based on body temperature data and ambient light data:

[0111] (9)

[0112] (10)

[0113] In the formula, Indicates light sensitivity characteristics, Indicates instantaneous changes in illumination. Indicates instantaneous temperature change. / Indicates the moment when the light intensity changes abruptly (i.e.) (the moment) Indicates time delay compensation. Indicates the staff on duty exist The denoised body temperature data corresponding to each moment. express Ambient lighting data at any given time.

[0114] In this embodiment, to further characterize / quantify ambient light data and the impact of light on the physical stress state of on-duty personnel, this embodiment can also obtain the melatonin concentration of on-duty personnel in a healthy state (i.e., day shift state) as a reference. Then, based on the effect of light intensity on melatonin concentration (light directly inhibits melatonin secretion through the retinohypothalamic pathway), the predicted value of melatonin concentration of on-duty personnel during night shifts is predicted, as follows:

[0115] (11)

[0116] In the formula, This indicates the duty personnel's duties during the night shift. Predicted melatonin concentration at time of day This indicates that under a healthy work-rest schedule (i.e., day shift), on-duty personnel should... Basal melatonin concentration at any given time express The effect of light exposure on melatonin concentration over time. express The effect of constant body temperature data on melatonin concentration.

[0117] In this embodiment, since the detection of melatonin concentration usually requires complex operations such as blood / saliva sampling and testing, it is not suitable for the real-time requirements of night shifts. Therefore, this technical solution pre-collects the melatonin concentration of on-duty personnel under healthy sleep conditions and fits the curve of melatonin basal concentration under healthy sleep conditions for the on-duty personnel:

[0118] (12)

[0119] In the formula, This represents the basal peak coefficient, which is the average peak value of melatonin basal concentration for on-duty personnel under healthy work and rest conditions. This represents the attenuation coefficient, typically ranging from 0.12 to 0.25h. -1 between, This indicates the time when melatonin secretion begins for staff on duty under a healthy work-rest schedule. This represents the minimum basal melatonin concentration of on-duty personnel under healthy work and rest conditions.

[0120] Based on the fitted data of the basal melatonin concentration of the on-duty personnel's healthy work-rest schedule (i.e., the basal melatonin concentration curve, which includes the entire 24 hours of both day and night shifts), and considering the effect of light intensity on melatonin concentration, the influence of light on melatonin concentration is calculated to correct the basal melatonin concentration.

[0121] (13)

[0122] In the formula, The light sensitivity coefficient represents the sensitivity of on-duty personnel to light. It can be fitted based on the linear relationship between light exposure and basal melatonin concentration changes during the day shift. In practice, it is typically between 0.003 and 0.008 lx. -1 between, express Light intensity at any given time.

[0123] In practical applications, besides light intensity, the body temperature of on-duty personnel also affects melatonin secretion. Typically, the body temperature of on-duty personnel and melatonin concentration exhibit an inverse circadian rhythm (i.e., the trough of the on-duty personnel's body temperature corresponds to the peak of melatonin concentration). Disruptions in the body temperature data of on-duty personnel during night shifts can interfere with melatonin secretion, causing changes in melatonin concentration. Therefore, by calculating the impact of body temperature data on melatonin concentration, the baseline melatonin concentration can be corrected.

[0124] (14)

[0125] In the formula, The body temperature correlation coefficient represents the strength of the effect of body temperature changes on melatonin concentration (a negative coefficient, reflecting an anti-phase relationship), and is typically measured to be between -0.8 and -0.3 pg / (mL·℃). This indicates that the staff on duty are during the night shift. Body temperature data at any time This indicates that the staff on duty are during the day shift. Body temperature data at any given time (which can be fitted using historical daytime body temperature data).

[0126] Thus, using the basal melatonin concentration curve as the basis for melatonin concentration, and by adjusting the influence of light on melatonin concentration and the influence of body temperature data on melatonin concentration, the basal melatonin concentration represented in the basal melatonin concentration curve is corrected using Equation (11) to obtain the predicted melatonin concentration value for the staff on night duty. Then, based on the predicted melatonin concentration value, and by combining light, body temperature, and melatonin concentration, the indirect characteristics of melatonin are determined as part of the characteristic data:

[0127] (15)

[0128] In the formula, Indicates the staff on duty The melatonin deviation rate, also known as the melatonin indirect characteristic, indicates the duty personnel's... Predicted melatonin concentration during the night shift This represents the average melatonin concentration during the regular nighttime rest period when the staff on duty are not on duty (this can be pre-collected and calibrated experimentally, and will not be elaborated here).

[0129] In this embodiment, feature extraction is performed on the cortisol data to obtain the rhythmic fluctuations and cumulative deviations corresponding to the cortisol data. These, as cortisol feature data corresponding to the cortisol data, may include:

[0130] Based on the cortisol data, the difference between the cortisol concentrations corresponding to the start and end times of the night shift for the on-duty personnel is determined as the circadian rhythm fluctuation;

[0131] Based on the cortisol data, the sum of the differences between the cortisol concentration of the on-duty personnel at the start time of their night shift and the preset reference concentration within the sixth preset time period is determined as the cumulative deviation.

[0132] In this embodiment, the difference between the cortisol concentrations corresponding to the start and end times of the night shift for on-duty personnel is first determined as the rhythm fluctuation:

[0133] (16)

[0134] In the formula, Indicates the staff on duty rhythmic fluctuations, , These represent the personnel on duty. At the start time of the night shift and termination time The corresponding cortisol concentration.

[0135] Then, the sum of the differences between the cortisol concentration of the on-duty personnel at the start time of their night shift within the sixth preset time period and the preset reference concentration is determined as the cumulative deviation:

[0136] (17)

[0137] In the formula, This indicates the sixth preset time period (in practical applications, it can be any 2-hour or 4-hour interval during the night shift, etc.). Indicates the cumulative deviation. This indicates the preset reference concentration of cortisol.

[0138] In step 230, the fatigue level of the on-duty personnel is determined based on the feature data, which serves as the result of the on-duty personnel's rhythm state detection. This may include:

[0139] When the feature data is within a preset range, the feature score corresponding to the feature data is set to the first preset score;

[0140] When the feature data is not in the preset range, the feature score corresponding to the feature data is set to the second preset score;

[0141] Summing all the first preset scores and the second preset scores yields the comprehensive score corresponding to the feature data;

[0142] Based on the comprehensive score, the fatigue level of the on-duty personnel is determined as the result of the rhythm state detection.

[0143] In this embodiment, each feature data has a corresponding preset interval. This preset interval represents the normal interval in which each feature data falls when the on-duty personnel are in a normal circadian rhythm state during the night shift. Among the feature data, the phase offset is typically... The amplitude deviation is usually 1. The rate of decrease in body temperature is usually The standard deviation of heart rate intervals is usually 100%. The root mean square of the difference between adjacent heartbeat intervals is usually 1. Frequency domain characteristics are usually Light sensitivity characteristics are usually Melatonin's indirect characteristics are usually Rhythmic fluctuations are usually The cumulative deviation is usually .

[0144] In this embodiment, for any feature data, when the feature data falls within the corresponding preset interval, the score for that feature data is 1 (i.e., the first preset score, which can be flexibly set according to user needs in actual applications); when the feature data does not fall within the corresponding preset interval, the score for that feature data is 0 (i.e., the second preset score, which can be flexibly set according to user needs in actual applications). Then, the scores of all feature data are summed to obtain a comprehensive score. Based on the comprehensive score, the fatigue level of the on-duty personnel is classified as the rhythm state detection result, providing a quantitative reference for subsequent on-duty personnel scheduling.

[0145] For example, the aforementioned feature data includes a total of ten items, with a total score of ten points. When the comprehensive score is 1 to 3 points, the fatigue level is Level 1, which represents mild fatigue of the on-duty personnel; when the comprehensive score is 4 to 7 points, the fatigue level is Level 2, which represents moderate fatigue of the on-duty personnel; and when the comprehensive score is 8 points or above, the fatigue level is Level 3, which represents severe fatigue of the on-duty personnel.

[0146] In this way, by calibrating the fatigue level of on-duty personnel based on feature data, the physical stress state of on-duty personnel during night shifts can be quantified, avoiding the physical burden caused by long-term reversed work schedules. This also makes it easier for managers to flexibly schedule shifts based on the fatigue level of on-duty personnel, thereby alleviating their physical burden.

[0147] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the electronic device 100 described above can be referred to the corresponding process of each step in the aforementioned method, and will not be elaborated further here.

[0148] This application also provides a computer program product, including a computer program that, when executed by processor 101, implements the above-described rhythm state detection method.

[0149] Based on the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by hardware or by using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various implementation scenarios of this application.

[0150] In summary, this application provides a method, electronic device, and program product for detecting rhythmic state. In this technical solution, multimodal vital sign data characterizing the physical stress state of on-duty personnel is first acquired. Then, feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data item. Finally, based on the feature data, the fatigue level of the on-duty personnel is determined as the result of their rhythmic state detection. Thus, using multimodal vital sign data as a reference indicator characterizing the physical stress / rhythmic state of on-duty personnel can improve the accuracy of judging their physical stress / rhythmic state and address the problem of insufficient accuracy in traditional methods of detecting the physical rhythmic state of on-duty personnel due to the single data type of vital signs.

[0151] In the embodiments provided in this application, it should be understood that the disclosed methods can also be implemented in other ways. The method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0152] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting rhythmic states, characterized in that, The method includes: Acquire multimodal vital signs data representing the physical stress state of on-duty personnel; Feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data in the multimodal vital sign data; Based on the characteristic data, the fatigue level of the on-duty personnel is determined, which serves as the result of the on-duty personnel's rhythm state detection.

2. The method according to claim 1, characterized in that, The multimodal vital signs data include the on-duty personnel's body temperature data, heart rate data, ambient light data, and cortisol data; Acquire multimodal vital signs data characterizing the physical stress state of on-duty personnel, including: The body temperature of the on-duty personnel is collected at a first preset frequency during a first preset time period and used as the body temperature data; The heart rate of the on-duty personnel is collected at a second preset frequency during a second preset time period, and used as the heart rate data. The light intensity of the on-duty personnel during the third preset time period is collected at a third preset frequency and used as the ambient light data; The cortisol concentration of the on-duty personnel during the fourth preset time period is collected at a fourth preset frequency and used as the cortisol data.

3. The method according to claim 2, characterized in that, Feature extraction is performed on the multimodal vital sign data to obtain the feature data corresponding to each vital sign data in the multimodal vital sign data, including: Feature extraction is performed on the body temperature data to obtain the phase offset and amplitude deviation between the body temperature data of the duty personnel during night duty and the reference body temperature data, as well as the rate of decrease of body temperature of the duty personnel during the fifth preset period during the night duty, which are used as the body temperature feature data corresponding to the body temperature data. Feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data; Based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain the light feature data corresponding to the ambient light data; Feature extraction is performed on the cortisol data to obtain the rhythm fluctuations and cumulative deviations corresponding to the cortisol data, which are used as the cortisol feature data corresponding to the cortisol data.

4. The method according to claim 3, characterized in that, Feature extraction is performed on the body temperature data to obtain the phase shift and amplitude deviation between the body temperature data of the on-duty personnel during night shifts and the reference body temperature data, as well as the rate of temperature decrease of the on-duty personnel during the fifth preset time period during the night shift. These are used as the body temperature feature data corresponding to the body temperature data, including: Temperature curves are fitted to the body temperature data and the reference body temperature data respectively to obtain the night shift curve corresponding to the body temperature data and the baseline curve corresponding to the reference body temperature data. The phase offset and the amplitude deviation are determined based on the baseline curve and the night shift curve. The rate of decrease in body temperature is determined based on the body temperature data.

5. The method according to claim 3, characterized in that, Feature extraction is performed on the heart rate data to obtain heart rate variability feature data corresponding to the heart rate data, including: Based on the heart rate data, determine the time-domain features in the heart rate variability feature data; The power spectrum was obtained by performing a Fourier transform on the heart rate data. In the power spectrum, frequency bands below a preset frequency are designated as low-frequency bands, and frequency bands above or equal to the preset frequency are designated as high-frequency bands. Based on the power corresponding to the low-frequency bands and the high-frequency bands, the frequency domain features in the heart rate variability feature data are determined.

6. The method according to claim 3, characterized in that, Based on the body temperature data and the ambient light data, feature extraction is performed on the ambient light data to obtain the light feature data corresponding to the ambient light data, including: Based on the body temperature data and the ambient light data, determine the light sensitivity characteristics in the light characteristic data that characterize the degree of influence of light intensity on body temperature.

7. The method according to claim 3, characterized in that, Feature extraction is performed on the cortisol data to obtain the rhythmic fluctuations and cumulative deviations corresponding to the cortisol data, which are used as the cortisol feature data corresponding to the cortisol data, including: Based on the cortisol data, the difference between the cortisol concentrations corresponding to the start and end times of the night shift for the on-duty personnel is determined as the circadian rhythm fluctuation; Based on the cortisol data, the sum of the differences between the cortisol concentration of the on-duty personnel at the start time of their night shift and the preset reference concentration within the sixth preset time period is determined as the cumulative deviation.

8. The method according to claim 1, characterized in that, Based on the aforementioned feature data, the fatigue level of the on-duty personnel is determined as the result of the on-duty personnel's rhythm state detection, including: When the feature data is within a preset range, the feature score corresponding to the feature data is set to the first preset score; When the feature data is not in the preset range, the feature score corresponding to the feature data is set to the second preset score; Summing all the first preset scores and the second preset scores yields the comprehensive score corresponding to the feature data; Based on the comprehensive score, the fatigue level of the on-duty personnel is determined as the result of the rhythm state detection.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory coupled together, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method as described in any one of claims 1 to 8.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 8.

Images