Digital construction site labor personnel state identification method based on digital twinning

Abstract

The invention discloses a digital construction site labor service personnel state identification method based on digital twinning. The method specifically comprises the following steps that all state data of labor service personnel are acquired and collected in an all-around mode through a data acquisition terminal; collected state data are transmitted and gathered to a central processing system through a wireless transmission technology; the data is accurately analyzed and identified through a data processing means of the central processing system; performing identification and early warning on the abnormal state of the labor service personnel by using a big data analysis technology; according to the invention, through the processing processes of obtaining, transmitting, processing, analyzing, identifying and early warning the data, the state data of the labor service personnel can be comprehensively obtained, the overall health condition of the labor service personnel can be comprehensively and dynamically monitored, the state of the labor service personnel can be effectively monitored, potential problems can be timely found and processed, and the working efficiency can be improved. The physical health of workers is guaranteed, and the management of construction site labor personnel is optimized.

Description

Technical Field

[0001] The present invention relates to the field of construction site safety technology, and specifically to a method for identifying the status of digital construction site laborers based on digital twins. Background Art

[0002] Full production is the theme of urban construction and development. With the progress of society and economic development, construction safety issues are receiving more and more attention and importance from the whole society. Doing a good job in production safety and ensuring the safety of life and property of construction workers are the premise and guarantee for the sustainable development of my country's national economy. All walks of life have never relaxed their efforts to ensure production and construction safety and protect the lives and property of construction workers from loss. At present, on construction sites, the personal safety and work management of construction workers have always been the most important issues for construction units.

[0003] Currently, when laborers are working on construction sites, it is difficult to rely solely on patrols to achieve comprehensive safety management due to the complex environment and large number of people on the construction site. Moreover, monitoring is only carried out through cameras, and it is impossible to effectively analyze and utilize the monitoring information. The monitoring cameras are just for decoration, and it is also difficult to effectively identify and judge the status of laborers on the construction site, affecting the actual personal safety of construction workers. Summary of the Invention

[0004] The present invention provides a method for identifying the status of digital construction site laborers based on digital twins, which can effectively solve the problem raised in the above background technology that when current laborers are working on the construction site, it is difficult to rely on simple personnel patrols to achieve comprehensive management of safety due to the complex environment of the construction site and the large number of personnel. Moreover, monitoring is only carried out through cameras, and the monitoring information cannot be effectively analyzed and utilized. The monitoring cameras are just decorations, and it is also difficult to effectively identify and judge the status of construction site laborers, which affects the actual personal safety of construction workers.

[0005] To achieve the above objectives, the present invention provides the following technical solutions: a method for identifying the status of digital construction workers based on digital twins, which relies on multiple on-site data collection terminals to comprehensively collect various status data of workers on the construction site. With the help of advanced recognition and analysis technology, it accurately analyzes and identifies workers, responds to abnormal conditions with alarms, and collects corresponding intervention and management measures for abnormal conditions;

[0006] The specific steps include:

[0007] Step 1: Use the data collection terminal to comprehensively acquire and collect various status data of labor personnel;

[0008] Step 2: Transmitting the collected status data to the central processing system through wireless transmission technology;

[0009] Step 3: Use the data processing methods of the central processing system to accurately analyze and identify the data;

[0010] Step 4: Use big data analysis technology to identify and issue early warnings on abnormal conditions of laborers;

[0011] Step 5: Promptly alert and respond to abnormal conditions of labor personnel, and transmit warning information to on-site terminal equipment.

[0012] According to the above technical solution, in step one, when collecting various status data of the labor personnel through the data collection terminal, the status data of the labor personnel is mainly obtained through the data collection terminal composed of high-definition cameras, thermal imaging sensors and smart wearable devices.

[0013] According to the above technical solution, in step 1, when collecting data through a high-definition camera, the high-definition camera is placed on the construction site to collect visual feature information of the construction workers' behavior, position information, and facial expressions during their work, thereby capturing important events and situations in the workers' working environment;

[0014] When HD cameras are deployed on the construction site, it is necessary to ensure that HD cameras are deployed at key locations on the construction site to ensure full coverage and maximize the comprehensiveness of data capture.

[0015] When collecting data through thermal imaging sensors, thermal imaging sensors are installed in key areas to monitor the body temperature of workers working on the construction site in real time, and promptly screen and identify potential health abnormalities of workers. By identifying potential health abnormalities, the spread of infectious diseases is prevented and the health of workers is ensured to be good. Abnormal health conditions include fever.

[0016] When collecting data through smart wearable devices, the workers' heart rate, electrocardiogram, number of steps, and fatigue level are collected in real time through the smart devices they wear during work, enabling comprehensive dynamic monitoring of the workers' different physiological parameters.

[0017] In addition, when workers wear smart devices to obtain their status, the smart devices support long-term monitoring and preliminary health warnings, reminding workers if their work intensity is too high or they are feeling unwell.

[0018] In order to ensure comprehensive data collection on the construction site, high-definition cameras need to cover key areas, ensure the comprehensiveness of the data and no blind spots, and optimize the camera layout.

[0019] The effective field of view of each camera is a circle with a radius of r in meters, and the area it covers is A = πr 2 , the total area of the construction site is Atotal, the total coverage area of the camera is ∑Acamera, then the total coverage rate CR can be calculated as:

[0020]

[0021] At the same time, thermal imaging sensors are mainly used to detect changes in the body temperature of laborers, and to promptly detect potential health abnormalities, such as fever. The health screening formula is as follows:

[0022] The abnormal body temperature index (TAI) is calculated by measuring the worker's body temperature (T) using a thermal imaging sensor and comparing it with the baseline temperature (T) which is 37°C.

[0023]

[0024] If the TAI exceeds 5% and the body temperature changes by more than 1.85°C, it means that the body temperature is abnormal and there is a fever or other health risks. The system will trigger an alert and prompt further health screening or arrange rest;

[0025] Smart wearable devices can monitor workers' heart rate, steps, electrocardiogram, and fatigue level in real time to ensure comprehensive and dynamic tracking of their physical condition. However, it is necessary to calculate the workers' fatigue index (FI).

[0026] Smart devices assess workers' fatigue levels by monitoring heart rate (HR) changes in real time. The calculation formula is as follows:

[0027]

[0028] HR current heart rate: current heart rate;

[0029] HR resting heart rate: resting heart rate;

[0030] HR maximum heart rate: maximum heart rate;

[0031] When the FI value exceeds 75%, it means that the worker is in a high state of fatigue, and the system will issue an early warning to rest or adjust the task;

[0032] The number of steps, activity intensity, and environmental factors are combined to assess the workload of workers and form a workload index. The formula is as follows:

[0033]

[0034] Step Current step number: current number of steps or exercise amount;

[0035] Step setting step: set the target number of steps or activity amount;

[0036] HR current heart rate: current heart rate;

[0037] HR maximum heart rate: maximum heart rate;

[0038] Tcurrent temperature: current ambient temperature;

[0039] Normal temperature: The most suitable operating temperature is 20℃-25℃;

[0040] If the WI exceeds 70%, it means that the worker has a heavy workload, and the system will remind him to reduce the intensity of work or provide rest time;

[0041] Finally, the comprehensive health assessment index (OHI) is calculated by integrating the multi-dimensional data of body temperature, heart rate, and workload. The formula is as follows:

[0042] OHI=W1×TAI+W2×FI+W3×WI

[0043] Among them, W1W2W3 are the weights of each indicator;

[0044] TAI is the temperature abnormality index;

[0045] FI is fatigue index;

[0046] WI is the workload index;

[0047] When the OHI exceeds 75%, the system will issue a health warning to remind managers and workers to pay attention to health risks;

[0048] Since workers often work for long periods of time at high intensity, smart devices can also monitor their health over time and provide health trend analysis. Based on continuous data, the system calculates the cumulative fatigue index (CFI) to analyze workers' health trends:

[0049]

[0050] FI i is the fatigue index on day i;

[0051] N is the number of monitoring days;

[0052] CFI calculation results:

[0053] 0-200: Normal fatigue level. When the CFI is within this range, it means that the worker's fatigue level is low, his health is good, and he is suitable to continue working.

[0054] 200-400: Moderate fatigue. When the CFI is in this range, it means that the worker has begun to accumulate a certain amount of fatigue. Although it is not yet excessively fatigued, it is necessary to pay attention to their health status and may need to take appropriate rest or adjust the work intensity.

[0055] 400-600: High fatigue level. When the CFI exceeds this value, it means that the worker has accumulated a high level of fatigue and is at high health risk. In this case, appropriate rest or adjustment of work plan should be taken, and the need for health examination should be evaluated.

[0056] 600 or above: Excessive fatigue. A CFI of more than 600 indicates that the worker has accumulated excessive fatigue. In this case, the system should immediately issue a health warning and strongly recommend rest or health check-up.

[0057] When the CFI exceeds 500, the system issues a health warning, prompting workers to take a break or adjust their work plans;

[0058] When the CFI exceeds 600, the system will issue a severe fatigue warning, requiring an immediate health check and rest;

[0059] The CFI represents the cumulative fatigue of workers over a period of time. It is calculated based on data from several consecutive days or weeks. The higher the CFI, the more accumulated fatigue the workers have and the higher the health risks they may face.

[0060] The state identification of construction site workers also includes assessment of psychological state and behavior prediction;

[0061] Mental fatigue is not only determined by heart rate and activity level, but also takes into account the worker's continuous working time, rest conditions, and heart rate fluctuations. Adjusting various indicators based on real-time data makes the prediction more dynamic and personalized. The formula is as follows:

[0062]

[0063] AMHS is the Adaptive Mental Health Score model;

[0064] x i (t) represents the value of the i-th indicator at time t;

[0065] w i (t) represents the dynamic weight of the i-th indicator, and the weight can be automatically adjusted according to the current data and historical data through the algorithm;

[0066] n is the number of all indicators involved in the calculation;

[0067] AMHS calculation results:

[0068] 0-40%: Good mental state. This range indicates that the worker's mental health is good, his emotions are stable, and his work pressure is moderate. At this time, the system will not issue any health warnings;

[0069] 40%-70%: Mild mental fatigue. When the AMHS is within this range, workers may feel some stress or mild mood swings. Although it will not seriously affect their work, they need to pay attention to their mental health and may need proper rest and psychological counseling.

[0070] 70%-90%: Moderate mental fatigue. When workers are in this range, they may be facing greater psychological pressure or emotional fluctuations, which may affect their work efficiency. At this time, measures need to be taken, such as arranging rest, reducing work intensity, or providing psychological counseling;

[0071] Above 90%: Severe mental fatigue. When the AMHS exceeds 90%, it indicates that the worker's mental fatigue and stress are at a very high level. Anxiety, depression, emotional instability and other problems may occur. At this time, intervention measures must be taken immediately, which may require adjusting work tasks, providing psychological support, or enforcing rest;

[0072] When AMHS exceeds 70%, the system will issue a warning of mild to moderate mental fatigue, prompting workers to take a rest or seek psychological counseling;

[0073] When AMHS exceeds 90%, the system will issue a warning of severe mental fatigue, requiring immediate psychological intervention measures or adjustment of work tasks;

[0074] When CFI and AMHS are combined, AMHS is the main reference. When AMHS exceeds 70%, a warning is issued to prompt workers to rest or receive psychological counseling. When AMHS exceeds 90%, construction will be stopped regardless of the CFI value.

[0075] According to the above technical solution, in step two, the various status data collected by various on-site data acquisition terminals are safely and efficiently transmitted to the central processing system through wireless transmission technology. Before the status data is transmitted to the central processing system, it is also necessary to preliminarily deal with the connection and data compatibility issues of the hardware equipment to ensure that the status data is smoothly transmitted to the central processing system.

[0076] According to the above technical solution, in step 2, the various status data include visual feature information of behavioral movements, location information and facial expressions collected by high-definition cameras, body temperature status information collected by thermal imaging sensors, and physiological parameter information of heart rate, electrocardiogram, exercise steps and fatigue level collected by smart wearable devices;

[0077] Wireless transmission technologies include Wi-Fi, Bluetooth or dedicated wireless networks.

[0078] According to the above technical solution, step three, when accurately analyzing and identifying all data transmitted to the central processing system, specifically includes using computer vision technology to analyze real-time images and video data captured by high-definition cameras, and using deep learning algorithms to analyze physiological parameter data obtained by thermal imaging sensors and smart wearable devices;

[0079] When using computer vision technology to analyze data, real-time images and video data captured by high-definition cameras are analyzed to identify the behavior and location information of laborers;

[0080] When performing data analysis through deep learning algorithms, the physiological parameter data obtained by thermal imaging sensors and smart wearable devices is analyzed to monitor people's dangerous actions, abnormal heart rates and fatigue.

[0081] According to the above technical solution, in step three, after analyzing the data through computer vision technology and deep learning algorithms, it is necessary to combine the data analysis results to identify the behavioral status and physical condition of the labor personnel.

[0082] According to the above technical solution, in step 4, when performing abnormal status analysis, big data analysis technology is used to conduct in-depth comprehensive analysis and evaluation of various types of data aggregated to the central processing system, specifically including fatigue work identification, violation behavior monitoring, and abnormal health status monitoring;

[0083] Fatigue work recognition is a system that automatically identifies workers' fatigue during work by analyzing their movement patterns, facial expressions, and physiological data, including changes in heart rate and physiological activity.

[0084] Violation monitoring uses image recognition technology to monitor whether workers have violated safety regulations and promptly expose any violations.

[0085] Abnormal health status monitoring: Through the collected body temperature data and other physiological parameters, the signs of cough and high fever and their duration can be quickly identified.

[0086] According to the above technical solution, in step five, when alarming and responding to abnormal conditions of labor personnel, according to the thresholds and rules set within the system, when the central processing system identifies that the labor personnel are in abnormal conditions such as fatigue work, illegal behavior or physical discomfort, and when any of the abnormal conditions exists, the central processing system triggers the alarm in time and sends the relevant information to the terminal device of the construction site manager so that the manager can take corresponding measures to intervene and manage in time.

[0087] According to the above technical solution, in step five, when taking intervention and management measures, the determination is mainly based on the abnormal status feedback from the alarm content. Specific intervention and management measures include: suspending operations to provide rest, reallocating work tasks, strengthening on-site safety education, and providing medical assistance in a timely manner.

[0088] Compared with the prior art, the present invention has the following beneficial effects:

[0089] The present invention uses high-definition cameras, thermal imaging sensors, and smart wearable devices to comprehensively collect various status data of laborers on the construction site. The central processing system uses advanced computer vision algorithms, deep learning models, and data analysis technologies to accurately analyze and identify the collected behavioral and physical conditions of the personnel. When abnormal conditions such as fatigue, illegal behavior, or physical discomfort are identified, the central processing system immediately triggers an alarm and sends the relevant information to the terminal device of the construction site manager, so that corresponding measures can be taken in a timely manner for intervention and management, thereby improving the efficiency and safety of construction site management.

[0090] Through the process of data acquisition, transmission, processing, analysis, identification and early warning, we can achieve comprehensive acquisition of labor personnel status data, ensure comprehensive dynamic monitoring of the overall health of labor personnel, effectively monitor the status of labor personnel, timely discover and deal with potential problems, protect the health of workers, optimize the management of construction site labor personnel, ensure personnel safety and work efficiency, and improve the safety and reliability of engineering construction;

[0091] The optimized layout of high-definition cameras ensures full coverage of the construction site and avoids the appearance of blind spots, especially in high-risk operation areas such as high-altitude operation areas and mechanical operation areas. It maximizes the comprehensiveness of data collection. By calculating the total coverage rate CR, it can ensure that the camera coverage rate reaches more than 90%, thereby achieving accurate monitoring of personnel behavior and location information. The key layout of high-risk areas further ensures the safety of high-risk operators.

[0092] Thermal imaging sensors can monitor workers' body temperature changes in real time and calculate the abnormal temperature index (TAI). When the temperature exceeds the set threshold, the system can issue an early warning, reminding management personnel to conduct health screenings or arrange rest for workers, ensuring that workers' health problems are discovered and addressed in a timely manner.

[0093] By combining data such as step count, heart rate, and ambient temperature, the Workload Index (WI) can assess workers' work intensity. When the WI exceeds a set threshold, the system will issue a reminder to guide workers to appropriately reduce their work intensity or increase their rest time, thereby avoiding health problems caused by excessive workload.

[0094] By combining the abnormal body temperature index (TAI), fatigue index (FI), and workload index (WI), the comprehensive health assessment index (OHI) can comprehensively assess the health status of workers. When the OHI exceeds the set threshold, the system will issue a health warning, reminding managers to intervene in the health of workers or adjust work arrangements, thereby effectively preventing accidents caused by fatigue, overwork, or abnormal health.

[0095] Through the integration of multiple data collection terminals and the introduction of the adaptive mental health scoring model AMHS, the entire system has achieved comprehensive dynamic monitoring of workers from physical health to mental health. This can not only timely detect health problems such as abnormal body temperature, excessive fatigue, and psychological stress of workers, but also automatically adjust health assessment strategies based on data, and provide real-time early warning and intervention suggestions for construction site managers. The system has effectively improved the health and safety of workers, reduced the risk of accidents caused by health problems, and ensured the safe and efficient operation of the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0097] In the attached figure:

[0098] Figure 1 is a flowchart of the steps of the identification method of the present invention;

[0099] Figure 2 It is a composition framework diagram of the state recognition of the present invention. DETAILED DESCRIPTION

[0100] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0101] Example: Figure 1-2 As shown, the present invention provides a technical solution, a method for identifying the status of digital construction workers based on digital twins. Relying on multiple on-site data collection terminals, it comprehensively collects various status data of workers on the construction site. With the help of advanced recognition and analysis technology, it accurately analyzes and identifies workers, responds to abnormal conditions with alarms, and collects corresponding intervention management measures for abnormal conditions.

[0102] The specific steps include:

[0103] Step 1: Use the data collection terminal to comprehensively acquire and collect various status data of labor personnel;

[0104] Step 2: Transmitting the collected status data to the central processing system through wireless transmission technology;

[0105] Step 3: Use the data processing methods of the central processing system to accurately analyze and identify the data;

[0106] Step 4: Use big data analysis technology to identify and issue early warnings on abnormal conditions of laborers;

[0107] Step 5: Promptly alert and respond to abnormal conditions of labor personnel, and transmit warning information to on-site terminal equipment.

[0108] Based on the above technical solution, in step one, when collecting various status data of labor personnel through the data collection terminal, the status data of labor personnel are mainly obtained through the data collection terminal composed of high-definition cameras, thermal imaging sensors and smart wearable devices.

[0109] Based on the above technical solution, in step 1, when collecting data through high-definition cameras, high-definition cameras are placed on the construction site to collect visual feature information of the workers' behavior, position information, and facial expressions during their work, so as to capture important events and situations in the workers' working environment;

[0110] When HD cameras are deployed on the construction site, it is necessary to ensure that HD cameras are deployed at key locations on the construction site to ensure full coverage and maximize the comprehensiveness of data capture.

[0111] When collecting data through thermal imaging sensors, thermal imaging sensors are installed in key areas to monitor the body temperature of workers working on the construction site in real time, and promptly screen and identify potential health abnormalities of workers. By identifying potential health abnormalities, the spread of infectious diseases is prevented and the health of workers is ensured to be good. Abnormal health conditions include fever.

[0112] When collecting data through smart wearable devices, the workers' heart rate, electrocardiogram, number of steps, and fatigue level are collected in real time through the smart devices they wear during work, enabling comprehensive dynamic monitoring of the workers' different physiological parameters.

[0113] In addition, when workers wear smart devices to obtain their status, the smart devices support long-term monitoring and preliminary health warnings, reminding workers if their work intensity is too high or they are feeling unwell.

[0114] In order to ensure comprehensive data collection on the construction site, high-definition cameras need to cover key areas, ensure the comprehensiveness of the data and no blind spots, and optimize the camera layout.

[0115] The effective field of view of each camera is a circle with a radius of r in meters, and the area it covers is A = πr 2 , assuming that the total area of the construction site is Atotal and the total coverage area of the cameras is ∑Acamera, the total coverage rate CR can be calculated as:

[0116]

[0117] To ensure full coverage, the ideal CR value should reach more than 90%, especially for high-risk and complex areas, high-altitude operation areas, and mechanical operation areas, where additional focus should be placed;

[0118] At the same time, thermal imaging sensors are mainly used to detect changes in the body temperature of laborers, and to promptly detect potential health abnormalities, such as fever. The health screening formula is as follows:

[0119] The abnormal body temperature index (TAI) is calculated by measuring the worker's body temperature (T) using a thermal imaging sensor and comparing it with the baseline temperature (T) which is 37°C.

[0120]

[0121] If the TAI exceeds 5% and the body temperature changes by more than 1.85°C, it means that the body temperature is abnormal and there may be fever or other health risks. The system will trigger an early warning, prompting further health screening or arranging rest.

[0122] Smart wearable devices can monitor workers’ heart rate, steps, electrocardiogram and fatigue level in real time to ensure comprehensive dynamic tracking of their physical status. However, it is necessary to calculate the workers’ fatigue index (FI).

[0123] Smart devices assess workers' fatigue levels by monitoring heart rate (HR) changes in real time. The calculation formula is as follows:

[0124]

[0125] HR current heart rate: current heart rate;

[0126] HR resting heart rate: resting heart rate;

[0127] HRmax: Maximum heart rate, which can usually be estimated by HRmax = 220 - age;

[0128] When the FI value exceeds 75%, it means that the worker is in a high state of fatigue, and the system will issue an early warning to rest or adjust the task;

[0129] The number of steps, activity intensity, and environmental factors are combined to assess the workload of workers and form a workload index. The formula is as follows:

[0130]

[0131] Step Current step number: current number of steps or exercise amount;

[0132] Step setting step: set the target number of steps or activity amount;

[0133] HR current heart rate: current heart rate;

[0134] HR maximum heart rate: maximum heart rate;

[0135] Tcurrent temperature: current ambient temperature;

[0136] Normal temperature: The most suitable operating temperature is 20℃-25℃;

[0137] If the WI exceeds 70%, it means that the worker has a heavy workload and the system will remind him to reduce the work intensity or provide rest time;

[0138] Finally, a comprehensive health assessment index (OHI) is calculated based on multi-dimensional data such as body temperature, heart rate, and workload. The formula is as follows:

[0139] OHI=W1×TAI+W2×FI+W3×WI

[0140] Among them, W1W2W3 are the weights of each indicator;

[0141] TAI is the temperature abnormality index;

[0142] FI is fatigue index;

[0143] WI is the workload index;

[0144] When the OHI exceeds 75%, the system will issue a health warning to remind managers and workers to pay attention to health risks;

[0145] Since workers often work long hours and at high intensity, smart devices can also monitor their health over time and provide health trend analysis. Based on continuous data, the system can calculate the cumulative fatigue index (CFI) to analyze workers' health trends:

[0146]

[0147] FI i is the fatigue index on day i;

[0148] N is the number of monitoring days;

[0149] CFI calculation results:

[0150] 0-200: Normal fatigue level. When the CFI is within this range, it means that the worker's fatigue level is low, his health is good, and he is suitable to continue working.

[0151] 200-400: Moderate fatigue. When the CFI is in this range, it means that the worker has begun to accumulate a certain amount of fatigue. Although it is not yet excessively fatigued, it is necessary to pay attention to their health status and may need to take appropriate rest or adjust the work intensity.

[0152] 400-600: High fatigue level. When the CFI exceeds this value, it means that the worker has accumulated a high level of fatigue and is at high health risk. In this case, appropriate rest or adjustment of work plan should be taken, and the need for health examination should be evaluated.

[0153] 600 or above: Excessive fatigue. A CFI of more than 600 indicates that the worker has accumulated excessive fatigue. In this case, the system should immediately issue a health warning and strongly recommend rest or health check-up.

[0154] When the CFI exceeds 500, the system issues a health warning, prompting workers to take a break or adjust their work plans;

[0155] When the CFI exceeds 600, the system will issue a severe fatigue warning, requiring an immediate health check and rest;

[0156] The CFI represents the cumulative fatigue of workers over a period of time. It is calculated based on data from several consecutive days or weeks. The higher the CFI, the more accumulated fatigue the workers have and the higher the health risks they may face.

[0157] The state identification of construction site workers also includes assessment of psychological state and behavior prediction;

[0158] Mental fatigue is not only determined by heart rate and activity level, but also takes into account the worker's continuous working time, rest conditions, and heart rate fluctuations. Adjusting various indicators based on real-time data makes the prediction more dynamic and personalized. The formula is as follows:

[0159]

[0160] AMHS is the Adaptive Mental Health Score model;

[0161] x i (t) represents the value of the i-th indicator at time t, such as heart rate, activity intensity, voice emotion, etc.;

[0162] w i(t) represents the dynamic weight of the i-th indicator. The weight can be automatically adjusted according to the current data and historical data through an algorithm, such as using reinforcement learning or adaptive filtering technology;

[0163] n is the number of all indicators involved in the calculation, such as heart rate, gait, and voice emotion;

[0164] Through the above multi-dimensional data collection and calculation formula, comprehensive monitoring and timely warning of the health status of laborers can be achieved:

[0165] High-definition cameras ensure full coverage and avoid blind spots;

[0166] Thermal imaging sensors monitor body temperature changes in real time and detect health abnormalities in a timely manner;

[0167] Smart wearable devices provide multi-dimensional data such as heart rate, fatigue, and exercise for dynamic health monitoring.

[0168] Combining multiple indicators such as body temperature, fatigue index, workload, etc., a comprehensive health assessment index is generated to accurately predict potential health problems and issue early warnings.

[0169] This data fusion solution can greatly improve construction site safety, reduce health risks for workers, and improve work efficiency and productivity.

[0170] AMHS calculation results:

[0171] 0-40%: Good mental state. This range indicates that the worker's mental health is good, his emotions are stable, and his work pressure is moderate. At this time, the system will not issue any health warnings;

[0172] 40%-70%: Mild mental fatigue. When the AMHS is within this range, workers may feel some stress or mild mood swings. Although it will not seriously affect their work, they need to pay attention to their mental health and may need proper rest and psychological counseling.

[0173] 70%-90%: Moderate mental fatigue. When workers are in this range, they may be facing greater psychological pressure or emotional fluctuations, which may affect their work efficiency. At this time, measures need to be taken, such as arranging rest, reducing work intensity, or providing psychological counseling;

[0174] Above 90%: Severe mental fatigue. When the AMHS exceeds 90%, it indicates that the worker's mental fatigue and stress are at a very high level. Anxiety, depression, emotional instability and other problems may occur. At this time, intervention measures must be taken immediately, which may require adjusting work tasks, providing psychological support, or enforcing rest;

[0175] When AMHS exceeds 70%, the system will issue a warning of mild to moderate mental fatigue, prompting workers to take a rest or seek psychological counseling;

[0176] When AMHS exceeds 90%, the system will issue a warning of severe mental fatigue, requiring immediate psychological intervention measures or adjustment of work tasks;

[0177] When CFI and AMHS are combined, AMHS is the main reference. When AMHS exceeds 70%, a warning is issued to prompt workers to rest or receive psychological counseling. When AMHS exceeds 90%, construction will be stopped regardless of the CFI value.

[0178] Based on the above technical solution, in step two, the various status data collected by various on-site data acquisition terminals are safely and efficiently transmitted to the central processing system through wireless transmission technology. Before the status data is transmitted to the central processing system, it is necessary to preliminarily deal with the connection and data compatibility issues of the hardware equipment to ensure that the status data is smoothly transmitted to the central processing system.

[0179] Based on the above technical solution, in step 2, various status data include visual feature information of behavioral movements, location information and facial expressions collected by high-definition cameras, body temperature status information collected by thermal imaging sensors, and physiological parameter information of heart rate, electrocardiogram, exercise steps and fatigue level collected by smart wearable devices;

[0180] Wireless transmission technologies include Wi-Fi, Bluetooth or dedicated wireless networks.

[0181] Based on the above technical solution, step three involves accurately analyzing and identifying all data transmitted to the central processing system. This specifically involves using computer vision technology to analyze real-time images and video data captured by high-definition cameras, and using deep learning algorithms to analyze physiological parameter data obtained by thermal imaging sensors and smart wearable devices.

[0182] When using computer vision technology to analyze data, real-time images and video data captured by high-definition cameras are analyzed to identify the behavior and location information of laborers;

[0183] When performing data analysis through deep learning algorithms, the physiological parameter data obtained by thermal imaging sensors and smart wearable devices is analyzed to monitor people's dangerous actions, abnormal heart rates and fatigue.

[0184] Based on the above technical solution, in step three, after analyzing the data through computer vision technology and deep learning algorithms, it is necessary to combine the data analysis results to identify the behavioral status and physical condition of the laborers.

[0185] Based on the above technical solution, in step 4, when conducting abnormal status analysis, big data analysis technology is used to conduct in-depth comprehensive analysis and evaluation of various data aggregated to the central processing system, including fatigue work identification, violation monitoring, and abnormal health status monitoring;

[0186] Fatigue work recognition is a system that automatically identifies workers' fatigue during work by analyzing their movement patterns, facial expressions, and physiological data, including changes in heart rate and physiological activity.

[0187] Violation monitoring uses image recognition technology to monitor whether workers have violated safety regulations and promptly expose any violations.

[0188] Abnormal health status monitoring: Through the collected body temperature data and other physiological parameters, the signs of cough and high fever and their duration can be quickly identified.

[0189] Based on the above technical solution, in step five, when alarming and responding to abnormal conditions of laborers, according to the thresholds and rules set within the system, when the central processing system identifies that the laborers are in abnormal conditions such as fatigue, illegal behavior or physical discomfort, and any of the abnormal conditions exists, the central processing system will trigger the alarm in time and send the relevant information to the terminal device of the construction site manager so that the manager can take corresponding measures to intervene and manage in time.

[0190] Based on the above technical solution, in step five, when taking intervention and management measures, the decision is mainly based on the abnormal status feedback from the alarm content. Specific intervention and management measures include: suspending operations to provide rest, reallocating work tasks, strengthening on-site safety education, and providing timely medical assistance.

[0191] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for identifying the status of digital construction workers based on digital twins, characterized by: Relying on a variety of on-site data collection terminals, it comprehensively collects various status data of laborers on the construction site. With the help of advanced recognition and analysis technology, it accurately analyzes and identifies laborers, responds to abnormal conditions with alarms, and collects corresponding intervention management measures for abnormal conditions. The specific steps include: Step 1: Use the data collection terminal to comprehensively acquire and collect various status data of labor personnel; Step 2: Transmitting the collected status data to the central processing system through wireless transmission technology; Step 3: Use the data processing methods of the central processing system to accurately analyze and identify the data; Step 4: Use big data analysis technology to identify and issue early warnings on abnormal conditions of laborers; Step 5: Promptly alert and respond to abnormal conditions of labor personnel, and transmit warning information to on-site terminal equipment.

2. A method for identifying the status of digital construction workers based on digital twins according to claim 1, characterized in that: In the step 1, when collecting various status data of the labor personnel through the data collection terminal, the status data of the labor personnel is mainly obtained through the data collection terminal composed of a high-definition camera, a thermal imaging sensor and an intelligent wearable device.

3. The method for identifying the status of digital construction workers based on digital twins according to claim 2 is characterized by: In step 1, when collecting data through a high-definition camera, the high-definition camera is placed on the construction site to collect visual feature information of the construction workers' behavior, position information, and facial expressions during their work, thereby capturing important events and situations in the workers' working environment; When HD cameras are deployed on the construction site, it is necessary to ensure that HD cameras are deployed at key locations on the construction site to ensure full coverage and maximize the comprehensiveness of data capture. When collecting data through thermal imaging sensors, thermal imaging sensors are installed in key areas to monitor the body temperature of workers working on the construction site in real time, and promptly screen and identify potential health abnormalities of workers. By identifying potential health abnormalities, the spread of infectious diseases is prevented and the health of workers is ensured to be good. Abnormal health conditions include fever. When collecting data through smart wearable devices, the workers' heart rate, electrocardiogram, number of steps, and fatigue level are collected in real time through the smart devices they wear during work, enabling comprehensive dynamic monitoring of the workers' different physiological parameters. In addition, when workers wear smart devices to obtain their status, the smart devices support long-term monitoring and preliminary health warnings, reminding workers if their labor intensity is too high or they are feeling unwell; In order to ensure comprehensive data collection on the construction site, high-definition cameras need to cover key areas, ensure the comprehensiveness of the data and no blind spots, and optimize the camera layout. The effective field of view of each camera is a circle with a radius of r in meters, and the area it covers is A = πr 2 The total area of the construction site is A 总 , the total coverage area of the camera is ∑Acamera, then the total coverage rate CR can be calculated as: At the same time, thermal imaging sensors are mainly used to detect changes in the body temperature of laborers, and to promptly detect potential health abnormalities, such as fever. The health screening formula is as follows: The abnormal body temperature index (TAI) is calculated by measuring the worker's body temperature (T) using a thermal imaging sensor and comparing it with the baseline temperature (T) which is 37°C. If the TAI exceeds 5% and the body temperature changes by more than 1.85°C, it means that the body temperature is abnormal and there is a fever or other health risks. The system will trigger an alert and prompt further health screening or arrange rest; Smart wearable devices can monitor workers' heart rate, steps, electrocardiogram, and fatigue level in real time to ensure comprehensive and dynamic tracking of their physical condition. However, it is necessary to calculate the workers' fatigue index (FI). Smart devices assess workers' fatigue levels by monitoring heart rate (HR) changes in real time. The calculation formula is as follows: HR current heart rate: current heart rate; HR resting heart rate: resting heart rate; HR maximum heart rate: maximum heart rate; When the FI value exceeds 75%, it means that the worker is in a high state of fatigue, and the system will issue an early warning to rest or adjust the task; The number of steps, activity intensity, and environmental factors are combined to assess the workload of workers and form a workload index. The formula is as follows: Step Current step number: current number of steps or exercise amount; Step setting step: set the target number of steps or activity amount; HR current heart rate: current heart rate; HR maximum heart rate: maximum heart rate; Tcurrent temperature: current ambient temperature; Normal temperature: The most suitable operating temperature is 20℃-25℃; If the WI exceeds 70%, it means that the worker has a heavy workload, and the system will remind him to reduce the intensity of work or provide rest time; Finally, the comprehensive health assessment index (OHI) is calculated by integrating the multi-dimensional data of body temperature, heart rate, and workload. The formula is as follows: OHI=W1×TAI+W2×FI+W3×WI Among them, W1W2W3 are the weights of each indicator; TAI is the temperature abnormality index; FI is fatigue index; WI is the workload index; When the OHI exceeds 75%, the system will issue a health warning to remind managers and workers to pay attention to health risks; Since workers often work for long periods of time at high intensity, smart devices can also monitor their health over time and provide health trend analysis. Based on continuous data, the system calculates the cumulative fatigue index (CFI) to analyze workers' health trends: FI i is the fatigue index on day i; N is the number of monitoring days; CFI calculation results: 0-200: Normal fatigue level. When the CFI is within this range, it means that the worker's fatigue level is low, his health is good, and he is suitable to continue working. 200-400: Moderate fatigue. When the CFI is in this range, it means that the worker has begun to accumulate a certain amount of fatigue. Although it is not yet excessively fatigued, it is necessary to pay attention to their health status and may need to take appropriate rest or adjust the work intensity. 400-600: High fatigue level. When the CFI exceeds this value, it means that the worker has accumulated a high level of fatigue and is at high health risk. In this case, appropriate rest or adjustment of work plan should be taken, and the need for health examination should be evaluated. 600 or above: Excessive fatigue. A CFI of more than 600 indicates that the worker has accumulated excessive fatigue. In this case, the system should immediately issue a health warning and strongly recommend rest or health check-up. When the CFI exceeds 500, the system issues a health warning, prompting workers to take a break or adjust their work plans; When the CFI exceeds 600, the system will issue a severe fatigue warning, requiring an immediate health check and rest; The CFI represents the cumulative fatigue of workers over a period of time. It is calculated based on data from several consecutive days or weeks. The higher the CFI, the more accumulated fatigue the workers have and the higher the health risks they may face. The state identification of construction site workers also includes assessment of psychological state and behavior prediction; Mental fatigue is not only determined by heart rate and activity level, but also takes into account the worker's continuous working time, rest conditions, and heart rate fluctuations. Adjusting various indicators based on real-time data makes the prediction more dynamic and personalized. The formula is as follows: AMHS is the Adaptive Mental Health Score model; x i (t) represents the value of the i-th indicator at time t; w i (t) represents the dynamic weight of the i-th indicator, and the weight can be automatically adjusted according to the current data and historical data through the algorithm; n is the number of all indicators involved in the calculation; AMHS calculation results: 0-40%: Good mental state. This range indicates that the worker's mental health is good, his emotions are stable, and his work pressure is moderate. At this time, the system will not issue any health warnings; 40%-70%: Mild mental fatigue. When the AMHS is within this range, workers may feel some stress or mild mood swings. Although it will not seriously affect their work, they need to pay attention to their mental health and may need proper rest and psychological counseling. 70%-90%: Moderate mental fatigue. When workers are in this range, they may be facing greater psychological pressure or emotional fluctuations, which may affect their work efficiency. At this time, measures need to be taken, such as arranging rest, reducing work intensity, or providing psychological counseling; Above 90%: Severe mental fatigue. When the AMHS exceeds 90%, it indicates that the worker's mental fatigue and stress are at a very high level. Anxiety, depression, emotional instability and other problems may occur. At this time, intervention measures must be taken immediately, which may require adjusting work tasks, providing psychological support, or enforcing rest; When AMHS exceeds 70%, the system will issue a warning of mild to moderate mental fatigue, prompting workers to take a rest or seek psychological counseling; When AMHS exceeds 90%, the system will issue a warning of severe mental fatigue, requiring immediate psychological intervention measures or adjustment of work tasks; When CFI and AMHS are combined, AMHS is the main reference. When AMHS exceeds 70%, a warning is issued to prompt workers to rest or receive psychological counseling. When AMHS exceeds 90%, construction will be stopped regardless of the CFI value.

4. The method for identifying the status of digital construction workers based on digital twins according to claim 1 is characterized by: In the second step, the various status data collected by various on-site data collection terminals are safely and efficiently transmitted to the central processing system through wireless transmission technology. Before the status data is transmitted to the central processing system, it is necessary to preliminarily deal with the connection and data compatibility issues of the hardware equipment to ensure that the status data is smoothly transmitted to the central processing system.

5. The method for identifying the status of digital construction workers based on digital twins according to claim 4 is characterized by: In step 2, the various status data include visual feature information of behavioral movements, location information and facial expressions collected by high-definition cameras, body temperature status information collected by thermal imaging sensors, and physiological parameter information of heart rate, electrocardiogram, exercise steps and fatigue level collected by smart wearable devices; Wireless transmission technologies include Wi-Fi, Bluetooth or dedicated wireless networks.

6. The method for identifying the status of digital construction workers based on digital twins according to claim 1 is characterized by: Step three, when accurately analyzing and identifying all data transmitted to the central processing system, specifically includes using computer vision technology to analyze real-time images and video data captured by high-definition cameras, and using deep learning algorithms to analyze physiological parameter data obtained by thermal imaging sensors and smart wearable devices; When using computer vision technology to analyze data, real-time images and video data captured by high-definition cameras are analyzed to identify the behavior and location information of laborers; When performing data analysis through deep learning algorithms, the physiological parameter data obtained by thermal imaging sensors and smart wearable devices is analyzed to monitor people's dangerous actions, abnormal heart rates and fatigue.

7. The method for identifying the status of digital construction workers based on digital twins according to claim 6 is characterized by: In step three, after analyzing the data using computer vision technology and deep learning algorithms, it is necessary to combine the data analysis results to identify the behavioral status and physical condition of the labor personnel.

8. The method for identifying the status of digital construction workers based on digital twins according to claim 1 is characterized by: In step 4, when performing abnormal status analysis, big data analysis technology is used to conduct in-depth comprehensive analysis and evaluation of various types of data aggregated to the central processing system, including fatigue identification, violation monitoring, and abnormal health status monitoring; Fatigue work recognition is a system that automatically identifies workers' fatigue during work by analyzing their movement patterns, facial expressions, and physiological data, including changes in heart rate and physiological activity. Violation monitoring uses image recognition technology to monitor whether workers have violated safety regulations and promptly expose any violations. Abnormal health status monitoring: Through the collected body temperature data and other physiological parameters, the signs of cough and high fever and their duration can be quickly identified.

9. The method for identifying the status of digital construction workers based on digital twins according to claim 1 is characterized by: In step five, when alarming and responding to abnormal conditions of laborers, according to the thresholds and rules set within the system, when the central processing system identifies that the laborers are in abnormal conditions such as fatigue, illegal behavior or physical discomfort, and when any of these abnormal conditions exist, the central processing system will trigger an alarm in a timely manner and send relevant information to the terminal device of the construction site manager so that the manager can take corresponding measures to intervene and manage in a timely manner.

10. The method for identifying the status of digital construction workers based on digital twins according to claim 9 is characterized by: In step five, when taking intervention and management measures, the decision is mainly based on the abnormal status reported by the alarm content. Specific intervention and management measures include: suspending work to provide rest, reallocating work tasks, strengthening on-site safety education, and providing timely medical assistance.

Images