High-altitude operation state monitoring method and system and storage medium

Abstract

The invention relates to a high-altitude operation state monitoring method and system, computer equipment and a storage medium, and relates to the technical field of high-altitude operation. According to the method, the physiological state characteristic data and the motion characteristic data are acquired in real time for the high-altitude operation personnel, the acquired physiological state characteristic data and the motion characteristic data are processed to acquire the physiological state evaluation result and the motion state evaluation result, and finally the state evaluation score of the high-altitude operation personnel is acquired. And monitoring a health score, an emotion score and an activity score according to the state evaluation score, and sending out alarm information when the state evaluation score exceeds a preset threshold value, so that the working safety can be improved, accidents and injuries are reduced, the working efficiency is improved, the medical cost is reduced, and the life quality of overhead working personnel is improved.

Description

Technical Field

[0001] The present application relates to the technical field of aerial work, and in particular to a method, system and storage medium for monitoring the status of aerial work. Background Art

[0002] Aerial work involves multiple industries and fields such as electricity, chemical industry, railway, and construction. It requires aerial workers to perform high-altitude construction. The aerial work scene environment is harsh. If the aerial workers are in poor physical condition, dangerous accidents are likely to occur. Due to the particularity of aerial work, it is difficult to achieve manual monitoring. There is a lack of corresponding monitoring equipment on the market, and it is impossible to monitor the physiological and psychological state of aerial workers in real time. With the development of Internet of Things technology and wireless communication technology, some wearable devices have emerged, such as smart bracelets and smart glasses. These devices are portable in human body status monitoring. At present, they have been applied to elderly people's fall monitoring, heart rate monitoring, blood oxygen concentration monitoring, etc. Based on these sensors and monitoring methods, they are applied in the field of aerial work. It is necessary to integrate different sensor data, establish an aerial worker status evaluation model, and realize early warning of abnormal status of aerial workers. Summary of the invention

[0003] Based on this, a method, system and storage medium for monitoring the status of aerial work are provided to solve the technical problem that it is difficult to monitor the physical status of aerial workers during current aerial work, which leads to sudden changes in the physiological and psychological status of aerial workers and causes dangerous accidents.

[0004] On the one hand, a method for monitoring the status of aerial work is provided, the method comprising:

[0005] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0006] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0007] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0008] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0009] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0010] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0011] In one embodiment, the physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data including:

[0012] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0013] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0014] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0015] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0016] In one embodiment, fusing the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result includes:

[0017] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X sn is the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0018] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0019] In one embodiment, the motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0020] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0021] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0022] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0023] In one embodiment, fusing the motion feature data to form a motion data multi-dimensional vector, and using a deep neural network model to process the motion data multi-dimensional vector to obtain a motion state assessment result includes:

[0024] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0025] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0026] In one embodiment, before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes:

[0027] Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data;

[0028] The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering;

[0029] The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =axraw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0030] In one embodiment, the method further comprises:

[0031] Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data;

[0032] The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0033] In one embodiment, the method further comprises:

[0034] A position information collection module is set up to collect the position information of personnel working at heights.

[0035] On the other hand, a high-altitude operation state monitoring system is provided, the system is used to implement the high-altitude operation state monitoring method described above, the system includes a physiological state detection sensor, a motion state detection sensor, a wireless communication module, an intelligent terminal and a remote server;

[0036] The physiological state detection sensor includes an EEG signal acquisition module, an ECG signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module; the physiological state detection sensor is used to collect physiological state characteristic data of high-altitude workers, and the physiological state characteristic data includes EEG signal data, ECG signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0037] The motion state detection sensor includes an acceleration sensor and a gyroscope; the motion state detection sensor is used to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes motion angle data, speed data and acceleration data;

[0038] The physiological state detection sensor and the motion state detection sensor are connected to the smart terminal via the wireless communication module. The smart terminal includes a data fusion module, which is used to fuse the physiological state feature data to form a physiological data multi-dimensional vector. The data fusion module is used to fuse the motion feature data to form a motion data multi-dimensional vector.

[0039] The smart terminal is connected to the remote server via the wireless communication module. The remote server is provided with a deep neural network model. The remote server is used to obtain a status assessment score of the high-altitude workers based on the physiological status assessment results and the motion status assessment results. The status assessment score includes a health score, an emotional score and an activity score. When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0040] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0041] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0042] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0043] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0044] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0045] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0046] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0047] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0048] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0049] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0050] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0051] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0052] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0053] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0054] The above-mentioned high-altitude work status monitoring method, system and storage medium collect physiological state characteristic data and motion characteristic data of high-altitude workers in real time, process the collected physiological state characteristic data and motion characteristic data to obtain physiological state assessment results and motion state assessment results, and finally obtain the status assessment score of the high-altitude workers. The health score, emotion score and activity score are monitored respectively for the status assessment score. When the status assessment score exceeds the preset threshold, an alarm message is issued, which can improve work safety, reduce accidents and injuries, improve work efficiency, reduce medical costs and improve the quality of life of high-altitude workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 This is a flow chart of a method for monitoring the state of aerial work in one embodiment of the present application;

[0057] Figure 2 A schematic diagram of a path for data collection and transmission for implementing a method for monitoring the status of aerial work in one embodiment of the present application;

[0058] Figure 3 This is a structural block diagram of a high-altitude operation status monitoring system in one embodiment of the present application;

[0059] Figure 4 This is a diagram of the internal structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] In one embodiment, Figure 1 , Figure 2 As shown, a method for monitoring the status of aerial work is provided, comprising the following steps:

[0062] Step S1, setting a physiological state detection sensor to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0063] Step S2, fusing the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0064] Step S3, setting a motion state detection sensor to collect motion characteristic data of the aerial worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0065] Step S4, fusing the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state evaluation result;

[0066] Step S5, obtaining a status assessment score of the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score and an activity score;

[0067] Step S6: When the status evaluation score exceeds a preset threshold, an alarm message is issued.

[0068] In this embodiment, the physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data including:

[0069] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0070] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0071] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0072] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0073] The wireless communication methods include Bluetooth, ZigBee, Lora, etc. It supports networking and realizes the self-organizing network of various detection sensors and smart terminals.

[0074] In this embodiment, fusing the physiological state feature data to form a multidimensional vector of physiological data, and using a deep neural network model to process the multidimensional vector of physiological data to obtain a physiological state assessment result includes:

[0075] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X sn is the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0076] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0077] In this embodiment, the motion state detection sensor is set to collect motion characteristic data of the aerial workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0078] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0079] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0080] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0081] In this embodiment, fusing the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result includes:

[0082] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0083] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0084] In this embodiment, before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes:

[0085] Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data;

[0086] The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering;

[0087] The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0088] In this embodiment, the method further includes:

[0089] Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data;

[0090] The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R iis the time interval of the ith heartbeat peak. R is the heartbeat peak in the waveform collected by the ECG sensor.

[0091] like Figure 1 As shown, in this embodiment, the method further includes:

[0092] Step S7, setting a position information collection module to collect the position information of the height working personnel.

[0093] In the above-mentioned high-altitude work status monitoring method, by collecting physiological state characteristic data and motion characteristic data of the high-altitude workers in real time, the collected physiological state characteristic data and motion characteristic data are processed to obtain physiological state assessment results and motion state assessment results, and finally the status assessment score of the high-altitude workers is obtained. The health score, emotional score and activity score are monitored respectively for the status assessment score. When the status assessment score exceeds the preset threshold, an alarm message is issued, which can improve work safety, reduce accidents and injuries, improve work efficiency, reduce medical costs and improve the quality of life of high-altitude workers.

[0094] Since the above physiological detection and motion detection data come from different sensors, it is necessary to perform multimodal data fusion on these sensor data, including EEG signals, ECG signals, pulse, blood oxygen saturation, body temperature, acceleration and gyroscope data. This multimodal data fusion fully considers a variety of physiological and motion information to provide a more comprehensive status assessment for high-altitude workers.

[0095] The steps of data fusion are as follows:

[0096] Step 1: Data preprocessing: Use digital filtering technology to treat the collected sensor data as a time series, and construct digital filters such as low-pass filters, mean filters, and bilateral filters to filter the noise in the collected sensor data.

[0097] Step 2: Sensor data calibration, if there is offset or scaling error in the sensor data, calibration can be performed. A simple linear calibration formula is as follows, where a and b are calibration parameters.

[0098] Calibration formula:

[0099] y calibration =ax raw +b

[0100] In the formula, y calibration is the sensor value after calibration, x raw is the sensor value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0101] Step 3: Extract features from physiological data. According to the above steps, the data of the physiological detection sensor is used as a time series, and wavelet transform is used to extract frequency domain features.

[0102] Heart rate and heart rate variability (HRV) can be extracted from the ECG signal, pulse waveform features can be extracted from the pulse signal, and oxygenated hemoglobin saturation can be extracted from the blood oxygen saturation.

[0103] Take heart rate variability (HRV) as an example:

[0104] Heart rate variability (HRV) refers to the variation in the difference between successive heartbeat cycles or the variation in the speed of the heartbeat. It is determined by the length of two adjacent RR intervals, that is, the slight difference from the first heartbeat cycle to the next heartbeat cycle. (R is the peak heartbeat in the waveform collected by the ECG sensor)

[0105]

[0106] Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0107] Step 4: Fusion of physiological data: Fusion of feature data from different sensors to establish a multimodal data representation. Data fusion techniques, such as feature-level fusion or model-level fusion, can be used to integrate multi-source data into a multidimensional vector X. fused .

[0108] X fused =[X s1 ,X s2 ,…,X sn ]

[0109] Where, X sn The data collected by the physiological status detection sensor include: EEG, ECG, pulse, blood oxygen, body temperature, etc.

[0110] Step 5: Multimodal physiological state evaluation model, using deep neural network to process multimodal data. The input of the model is the fused multimodal data features, and the output is the physiological state evaluation result. This model can include multi-layer convolutional neural network (CNN) and fully connected layers to automatically learn the complex relationship between data.

[0111] formula:

[0112] Y = f(X fused )

[0113] Where Y is the comprehensive physiological state assessment result, and f is the deep neural network model.

[0114] Step 6: Extraction of motion state detection sensor data features: Extract features from the data collected by each sensor module to obtain motion features. For example, the acceleration modulus (vector length) and angular velocity modulus, as well as the angle, speed and acceleration of the motion can be calculated.

[0115] Step 7: Motion state detection sensor data fusion, fuse the feature data from the accelerometer and gyroscope to establish a multi-modal motion feature vector. Vector splicing or other fusion techniques can be used to integrate multi-source data into a multi-dimensional vector X M,fused .

[0116] X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ]

[0117] Where, X M,sn Data collected by motion state detection sensors, such as acceleration, gyroscope, etc.

[0118] Step 8: Multimodal operation and maintenance status evaluation model, using deep neural network to process multimodal motion data. The input of the model is the fused multimodal motion features, and the output is the motion status evaluation result. This model can include convolutional neural network (CNN), recurrent neural network (RNN) and fully connected layers to learn complex motion patterns and states.

[0119] formula:

[0120] M=f(X M,fused )

[0121] Where M is the comprehensive motion state evaluation result, and f is the deep neural network model.

[0122] Step 9: According to Steps 3 to 8, the physiological state evaluation model and the motion state evaluation model are obtained. The comprehensive features output by the deep learning model are used to evaluate the physiological state of the high-altitude workers. This includes heart health, breathing status, oxygen supply, whether the body temperature is normal, etc. The comprehensive features output by the deep learning model are used to evaluate the motion state of the high-altitude workers. This includes the recognition of different states such as stillness, walking, running, tilting, shaking, and posture detection.

[0123] According to the above steps, the use case demonstration is as follows:

[0124] The collected sensor data is used as input, including:

[0125] EEG(t): EEG signal at time t;

[0126] ECG(t): ECG signal at time t;

[0127] PPG(t): pulse signal at time t;

[0128] SpO2(t): blood oxygen saturation at time t;

[0129] Temp(t): body temperature at time t;

[0130] Acc(t): acceleration data at time t (including three axes);

[0131] Gyro(t): gyroscope data at time t (including three axes).

[0132] Step 11: Preprocess the sensor data collected above, including noise filtering and calibration. Noise filtering and calibration are performed on each sensor data to ensure the quality of the data.

[0133] Step 12: Signal processing and feature extraction:

[0134] HRV(t): Calculates heart rate variability (HRV).

[0135] EEG_Power(t): Calculates the spectral energy of the EEG signal.

[0136] PPG_Freq(t): Calculates the main frequency components of the pulse signal.

[0137] Activity_Intensity(t): Calculates activity intensity based on acceleration data.

[0138] Step 13: Data fusion, perform feature-level fusion to merge each feature into a multimodal feature vector.

[0139] Xfused(t)=[HRV(t),EEG_Power(t),PPG_Freq(t),SpO2(t),Temp(t),Activity_Intensity(t),Acc(t),Gyro(t)]

[0140] Step 14: Build a deep learning model, multiple-input multiple-output (MIMO) model: Use a deep neural network to jointly model multimodal data. The model includes multiple layers, including convolutional layers, recurrent layers, and fully connected layers. The model takes multimodal features as input and outputs a comprehensive state assessment result.

[0141] Y(t)=f(Xfused(t))

[0142] Where, Y(t): comprehensive state evaluation result at time t. f: deep neural network model.

[0143] Step 15: Comprehensive state assessment: The model outputs comprehensive state assessment results, including comprehensive health index, emotional state and activity state.

[0144] Health score: Health_Score(t)=fhealth(Y(t));

[0145] Emotion score: Emotion_Score(t)=femotion(Y(t));

[0146] Activity score: Activity_Score(t)=factivity(Y(t)).

[0147] t: time

[0148] Health_Score(t): This score is used to assess the physiological health of workers working at heights. It includes assessments of heart health, respiratory system, body temperature, etc. For example, by monitoring abnormal changes in heart rate, blood oxygen saturation, and body temperature, the algorithm can detect possible cardiovascular problems or fever symptoms. The higher the score, the better the health status.

[0149] Emotion score Emotion_Score(t): The emotion score is used to assess the emotional state of workers working at heights. It can be analyzed through EEG signals and deep learning models to detect anxiety, fatigue, or other emotional abnormalities. Changes in the emotion score can be used to identify the emotional responses of workers working at heights, thereby helping managers take appropriate support measures.

[0150] Activity_Score(t): The activity score is used to evaluate the activity status and posture of workers working at heights. By analyzing acceleration and gyroscope data, the algorithm can detect abnormal movement activity, dangerous postures, or excessive physical activity. This helps prevent sports-related injuries at work.

[0151] In the above algorithm use cases, the meanings of the various symbols are as follows:

[0152] EEG(t): EEG signal data;

[0153] ECG(t): electrocardiogram signal data;

[0154] PPG(t): pulse signal data;

[0155] SpO2(t): blood oxygen saturation data;

[0156] Temp(t): body temperature data;

[0157] Acc(t): acceleration data;

[0158] Gyro(t): gyroscope data;

[0159] HRV(t): heart rate variability data;

[0160] EEG_Power(t): EEG signal spectrum energy data;

[0161] PPG_Freq(t): main frequency component data of pulse signal;

[0162] Activity_Intensity(t): activity intensity data;

[0163] Xfused(t): multimodal feature vector;

[0164] Y(t): comprehensive status assessment result;

[0165] f: deep neural network model;

[0166] fhealth: physiological health assessment function;

[0167] femotion: emotional state evaluation function;

[0168] factivity: Activity state evaluation function.

[0169] The innovation of the height-worker status evaluation algorithm described in the present invention lies in that it integrates a variety of physiological and motion data, and uses a deep learning model to evaluate the status of height-workers in real time, providing a comprehensive status evaluation, thereby helping to improve work safety.

[0170] The intelligent terminal processes the detection sensors worn by the high-altitude workers in real time, monitors these status scores in real time, and triggers an alarm if an abnormal situation is found. The alarm information is sent to the remote server through the wireless communication module, and the intelligent terminal notifies the high-altitude workers and on-site supervisors through local voice reminders. For example, if the health score drops sharply, a heart health alarm will be issued; if the emotional score indicates extreme anxiety, an emotional tension alarm will be issued; if the activity score indicates a dangerous movement state, a dangerous activity alarm will be issued.

[0171] This application aims to solve the key problem of status monitoring of high-altitude workers, and has the following obvious advantages: by collecting physiological state characteristic data and motion characteristic data of high-altitude workers in real time, processing the collected physiological state characteristic data and motion characteristic data to obtain physiological state evaluation results and motion state evaluation results, and finally obtaining the status evaluation score of the high-altitude workers, monitoring the health score, emotion score and activity score respectively for the status evaluation score, and issuing an alarm message when the status evaluation score exceeds the preset threshold, which can improve work safety, reduce accidents and injuries, improve work efficiency, reduce medical costs and improve the quality of life of high-altitude workers:

[0172] Improve work safety: By integrating multi-sensor data and deep learning models, the present invention can monitor the physiological state, emotional state and movement state of high-altitude workers in real time. This helps to timely detect potential health problems, emotional abnormalities and dangerous movement behaviors, thereby improving the safety of high-altitude operations.

[0173] Reduce accidents and injuries: The real-time monitoring and alarm system of the present invention can promptly send out alarms to supervisors and aerial workers, and when abnormal conditions are detected, such as heart problems, emotional tension or dangerous postures, appropriate measures can be taken quickly. This helps reduce accidents and injuries and improves the safety of aerial work.

[0174] Improve work efficiency: The real-time status assessment system of the present invention can help supervisors better understand the status of aerial workers, so as to allocate work tasks and improve work efficiency. By reducing unnecessary rest time and reallocating tasks, the completion time of the work can be shortened, thereby improving work efficiency.

[0175] Reduced medical costs: By regularly monitoring the physiological status of workers working at heights, potential health problems can be detected early and preventive measures can be taken. This reduces medical costs because the need for emergency medical treatment and long-term care can be reduced.

[0176] Improve the quality of life of workers working at heights: This invention not only helps with job safety, but also helps improve the quality of life of workers working at heights. They can work at heights with more confidence, knowing that their health and emotional state are being monitored and supported.

[0177] In one embodiment, Figure 3 As shown, a high-altitude operation state monitoring system is provided, which is used to implement the high-altitude operation state monitoring method described above, and the system includes a physiological state detection sensor, a motion state detection sensor, a wireless communication module, an intelligent terminal and a remote server;

[0178] The physiological state detection sensor includes an EEG signal acquisition module, an ECG signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module; the physiological state detection sensor is used to collect physiological state characteristic data of high-altitude workers, and the physiological state characteristic data includes EEG signal data, ECG signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0179] The motion state detection sensor includes an acceleration sensor and a gyroscope; the motion state detection sensor is used to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes motion angle data, speed data and acceleration data;

[0180] The physiological state detection sensor and the motion state detection sensor are connected to the smart terminal via the wireless communication module. The smart terminal includes a data fusion module, which is used to fuse the physiological state feature data to form a physiological data multi-dimensional vector. The data fusion module is used to fuse the motion feature data to form a motion data multi-dimensional vector.

[0181] The smart terminal is connected to the remote server via the wireless communication module. The remote server is provided with a deep neural network model. The remote server is used to obtain a status assessment score of the high-altitude workers based on the physiological status assessment results and the motion status assessment results. The status assessment score includes a health score, an emotional score and an activity score. When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0182] The smart terminal is an embedded edge computing terminal, such as a smart phone, a tablet, a smart gateway, etc. The smart terminal communicates data with each of the detection modules described above through a low-power wireless communication module. Data is exchanged with a remote server through wireless communications such as 4G, 5G, and GPRS.

[0183] The remote server is used to manage the sensors and intelligent terminals used by high-altitude workers, and store the status evaluation results of high-altitude workers. The remote server can also provide alarm reminders for abnormal status information, historical data display, real-time status viewing and other functions.

[0184] In this embodiment, the physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data including:

[0185] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0186] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0187] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0188] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0189] In this embodiment, fusing the physiological state feature data to form a multidimensional vector of physiological data, and using a deep neural network model to process the multidimensional vector of physiological data to obtain a physiological state assessment result includes:

[0190] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X sn is the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0191] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0192] In this embodiment, the motion state detection sensor is set to collect motion characteristic data of the aerial workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0193] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0194] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0195] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0196] In this embodiment, fusing the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result includes:

[0197] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0198] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0199] In this embodiment, in this embodiment, the aerial work status monitoring system further includes: a digital filter and a data calibration module.

[0200] Before fusing the physiological state characteristic data and before fusing the motion characteristic data, it also includes: performing noise filtering on the physiological state characteristic data through a digital filter; judging whether there is an offset or scaling error in the noise-filtered physiological state characteristic data through a data calibration module, and if so, performing data calibration on the noise-filtered physiological state characteristic data; performing noise filtering on the motion state characteristic data through a digital filter; judging whether there is an offset or scaling error in the noise-filtered motion state characteristic data through a data calibration module, and if so, performing data calibration on the noise-filtered motion state characteristic data.

[0201] The calibration formula for calibrating the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0202] In this embodiment, the aerial work status monitoring system further includes: a heart rate variability analysis module.

[0203] The heart rate variability analysis module is used to extract heart rate and heart rate variability (HRV) from the electrocardiogram signal data, extract pulse waveform features from the pulse signal data, and extract oxygenated hemoglobin saturation from the blood oxygen saturation data.

[0204] The heart rate variability is determined by the time interval between two adjacent heartbeat peaks. Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0205] In this embodiment, the aerial work status monitoring system further includes: a location information acquisition module. The location information acquisition module supports GPS and Beidou positioning, and is mainly used to record the location information of aerial work personnel. The location information acquisition module is integrated with the intelligent terminal.

[0206] The position information collection module is used to collect the position information of the personnel working at high altitudes.

[0207] In the above-mentioned high-altitude work status monitoring system, by collecting physiological state characteristic data and motion characteristic data of the high-altitude workers in real time, the collected physiological state characteristic data and motion characteristic data are processed to obtain physiological state assessment results and motion state assessment results, and finally the status assessment score of the high-altitude workers is obtained. The health score, emotional score and activity score are monitored respectively for the status assessment score. When the status assessment score exceeds the preset threshold, an alarm message is issued, which can improve work safety, reduce accidents and injuries, improve work efficiency, reduce medical costs and improve the quality of life of high-altitude workers.

[0208] For the specific definition of the aerial work status monitoring system, please refer to the definition of the aerial work status monitoring method above, which will not be repeated here. Each module in the above-mentioned aerial work status monitoring system can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0209] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0210] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0211] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0212] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0213] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0214] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0215] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0216] In one embodiment, the computer program further implements the following steps when executed by a processor:

[0217] The physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data, including:

[0218] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0219] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0220] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0221] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] The fusing of the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result comprises:

[0224] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X snis the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0225] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0227] The motion state detection sensor is set to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0228] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0229] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0230] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0231] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0232] The fusing of the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result comprises:

[0233] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0234] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0235] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0236] Before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes:

[0237] Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data;

[0238] The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering;

[0239] The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0240] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0241] Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data;

[0242] The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0243] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0244] A position information collection module is set up to collect the position information of personnel working at heights.

[0245] For the specific limitations on the steps implemented when the computer program is executed by the processor, please refer to the limitations on the method for monitoring the status of aerial work above, which will not be repeated here.

[0246] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store aerial work status monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for monitoring the aerial work status is implemented.

[0247] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0248] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0249] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0250] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0251] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0252] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0253] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0254] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0255] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0256] The physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data, including:

[0257] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0258] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0259] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0260] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0261] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0262] The fusing of the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result comprises:

[0263] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X sn is the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0264] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0265] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0266] The motion state detection sensor is set to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0267] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0268] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0269] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0270] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0271] The fusing of the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result comprises:

[0272] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0273] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0274] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0275] Before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes:

[0276] Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data;

[0277] The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering;

[0278] The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0279] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0280] Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data;

[0281] The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0282] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0283] A position information collection module is set up to collect the position information of personnel working at heights.

[0284] For the specific limitations on the steps implemented when the processor executes the computer program, please refer to the limitations on the method for monitoring the status of aerial work above, which will not be repeated here.

[0285] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0286] A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data;

[0287] The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result;

[0288] A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data;

[0289] The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result;

[0290] Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score;

[0291] When the status assessment score exceeds a preset threshold, an alarm message is issued.

[0292] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0293] The physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data, including:

[0294] The physiological state detection sensor is configured to include an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module;

[0295] The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers;

[0296] The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers.

[0297] The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

[0298] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0299] The fusing of the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result comprises:

[0300] Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X snis the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data;

[0301] The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

[0302] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0303] The motion state detection sensor is set to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including:

[0304] The motion state detection sensor is configured to include an acceleration sensor and a gyroscope;

[0305] The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking;

[0306] The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

[0307] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0308] The fusing of the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result comprises:

[0309] Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data;

[0310] The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

[0311] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0312] Before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes:

[0313] Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data;

[0314] The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering;

[0315] The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

[0316] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0317] Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data;

[0318] The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

[0319] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0320] A position information collection module is set up to collect the position information of personnel working at heights.

[0321] For the specific limitations on the steps implemented when the computer program is executed by the processor, please refer to the limitations on the method for monitoring the status of aerial work above, which will not be repeated here.

[0322] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0323] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0324] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring the status of aerial work, characterized in that: include: A physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, wherein the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data; The physiological state characteristic data are integrated to form a multi-dimensional vector of physiological data, and a deep neural network model is used to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result; A motion state detection sensor is set to collect motion characteristic data of the high-altitude worker, wherein the motion characteristic data includes motion angle data, speed data and acceleration data; The motion feature data are integrated to form a motion data multi-dimensional vector, and a deep neural network model is used to process the motion data multi-dimensional vector to obtain a motion state evaluation result; Obtaining a status assessment score for the high-altitude worker according to the physiological status assessment result and the exercise status assessment result, wherein the status assessment score includes a health score, an emotion score, and an activity score; When the status assessment score exceeds a preset threshold, an alarm message is issued.

2. The method for monitoring the state of aerial work according to claim 1, characterized in that: The physiological state detection sensor is set to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data, including: The physiological state detection sensor is set to include an EEG signal acquisition module, an ECG signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module; The EEG signal acquisition module integrates the electrodes for EEG signal acquisition with the safety helmets worn by the high-altitude workers, supports wireless communication, and uses the EEG signal acquisition module to collect EEG signal data of the high-altitude workers; The ECG signal acquisition module uses button-type electrodes and supports wireless communication. The ECG signal acquisition module is attached to the upper arm, chest, and neck of the high-altitude workers to collect ECG signal data of the high-altitude workers. The pulse signal detection module, the blood oxygen saturation detection module and the body temperature detection module collect the pulse signal data, blood oxygen saturation data and body temperature data of the high-altitude workers in the form of a smart bracelet.

3. The method for monitoring the state of aerial work according to claim 2, characterized in that: The fusing of the physiological state characteristic data to form a multi-dimensional vector of physiological data, and using a deep neural network model to process the multi-dimensional vector of physiological data to obtain a physiological state assessment result comprises: Set the multidimensional vector of physiological data to X fused =[X s1 ,X s2 ,…,X sn ], where X sn is the physiological state characteristic data, and the subscript sn is the sequence number of the physiological state characteristic data; The physiological status evaluation result obtained is Y=f(X fused ), where f is a deep neural network model.

4. The method for monitoring the state of aerial work according to claim 1, characterized in that: The motion state detection sensor is set to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes the angle data, speed data and acceleration data of the motion, including: The motion state detection sensor is configured to include an acceleration sensor and a gyroscope; The acceleration sensor and the gyroscope are integrated with the wireless communication module and installed and fixed on the full-body safety belt worn by the high-altitude workers to detect the activity status data of the high-altitude workers; the activity status data includes stillness, walking, running, tilting and shaking; The acceleration modulus, angular velocity modulus, and the angle data, velocity data, and acceleration data of the motion are calculated using the activity state data.

5. The method for monitoring the state of aerial work according to claim 4, characterized in that: The fusing of the motion feature data to form a motion data multidimensional vector, and using a deep neural network model to process the motion data multidimensional vector to obtain a motion state assessment result comprises: Set the motion data multidimensional vector to X M,fused =[X M,s1 ,X M,s2 ,…,X M,sn ], where X M,sn is the motion state characteristic data, subscript M, sn is the sequence number of the motion state characteristic data; The obtained motion state evaluation result is M=f(X M,fused ), where f is a deep neural network model.

6. The method for monitoring the state of aerial work according to claim 1, characterized in that: Before fusing the physiological state characteristic data and before fusing the motion characteristic data, the method further includes: Perform noise filtering on the physiological state characteristic data by using a digital filter; determine whether there is an offset or scaling error in the noise-filtered physiological state characteristic data, and if so, perform data calibration on the noise-filtered physiological state characteristic data; The motion state characteristic data is subjected to noise filtering by a digital filter; and it is determined whether the motion state characteristic data after noise filtering has an offset or scaling error, and if so, data calibration is performed on the motion state characteristic data after noise filtering; The calibration formula for data calibration of the physiological state characteristic data after noise filtering or the motion state characteristic data after noise filtering is set as: calibration =ax raw +b; where y calibration is the value after calibration, x raw is the value before calibration, a is the calibration coefficient, and b is the deviation coefficient.

7. The method for monitoring the state of aerial work according to claim 1, characterized in that: The method further comprises: Extracting heart rate and heart rhythm variability (HRV) from the electrocardiogram signal data, extracting pulse waveform features from the pulse signal data, and extracting oxyhemoglobin saturation from the blood oxygen saturation data; The heart rate variability is determined by the duration of the interval between two adjacent heartbeat peaks. The heart rate variability is Where N is the number of heartbeat peaks, R i is the time interval of the ith heartbeat peak.

8. The method for monitoring the state of aerial work according to claim 1, characterized in that: The method further comprises: A position information collection module is set up to collect the position information of personnel working at heights.

9. A high-altitude operation status monitoring system, characterized in that: The system is used to implement the aerial work status monitoring method according to any one of claims 1 to 8, and the system includes a physiological status detection sensor, a motion status detection sensor, a wireless communication module, an intelligent terminal and a remote server; The physiological state detection sensor includes an electroencephalogram signal acquisition module, an electrocardiogram signal acquisition module, a pulse acquisition module, a blood oxygen saturation acquisition module and a body temperature acquisition module; The physiological state detection sensor is used to collect physiological state characteristic data of the high-altitude workers, and the physiological state characteristic data includes brain electroencephalogram signal data, electrocardiogram signal data, pulse signal data, blood oxygen saturation data and body temperature data; The motion state detection sensor includes an acceleration sensor and a gyroscope; the motion state detection sensor is used to collect motion characteristic data of the high-altitude workers, and the motion characteristic data includes motion angle data, speed data and acceleration data; The physiological state detection sensor and the motion state detection sensor are connected to the smart terminal via the wireless communication module. The smart terminal includes a data fusion module, which is used to fuse the physiological state feature data to form a physiological data multi-dimensional vector. The data fusion module is used to fuse the motion feature data to form a motion data multi-dimensional vector. The smart terminal is connected to the remote server via the wireless communication module. The remote server is provided with a deep neural network model. The remote server is used to obtain a status assessment score of the high-altitude workers based on the physiological status assessment results and the motion status assessment results. The status assessment score includes a health score, an emotional score and an activity score. When the status assessment score exceeds a preset threshold, an alarm message is issued.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images