A working condition simulation analysis method and system for human-machine-environment coupling

Abstract

The application provides a work condition simulation analysis method and system for human-machine-environment coupling, and relates to the technical field of simulation and emulation, comprising: simulating modeling of a closed confined space to be simulated, and dividing the closed confined space into multiple functional area modules; respectively performing environment disturbance simulation and task simulation in each functional area module, and obtaining feedback data corresponding to execution of each type of task; respectively performing subjective and objective weighting on the feedback data by using analytic hierarchy process and entropy weight method, and obtaining corresponding contribution indexes; determining corresponding data quality deduction items and coupling influence quantities based on current collection configuration conditions of the contribution indexes, and determining work efficiency state, recovery state and risk state of a tested object in combination with the contribution indexes; and generating an adjustment strategy based on the work efficiency state, the recovery state and the risk state, so as to adjust environment parameters or setting parameters of each functional area module.

Description

Technical Field

[0001] This invention relates to the field of simulation technology, and in particular to a method and system for simulating and analyzing working conditions in a human-machine-environment coupled manner. Background Technology

[0002] Complex work environments such as confined spaces and long-term monitoring spaces are typically characterized by limited spatial scale, insufficient natural environmental input, long task duration, and complex personnel activity types. In these environments, workers need to complete tasks and also perform recovery and adjustment within confined spaces. In actual engineering projects, once such spaces are built or put into use, it is usually difficult to repeatedly change the internal environmental conditions, spatial configuration, and operational strategies. It is also not advisable to directly subject personnel to repeated high-load or risky experiments under real complex working conditions. Therefore, before determining the actual engineering environment, it is necessary to build an experimental platform capable of simulating actual working conditions. This platform can reproduce typical work and recovery environments under controllable conditions, and through experiments, obtain the relationship between personnel status, environmental parameters, and task performance. This provides a basis for subsequent space design, environmental control, task organization, and recovery strategy optimization.

[0003] Existing human factors testing platforms or environmental simulation systems can usually control some environmental factors, but they mostly focus on testing during the work task phase. They lack collaborative simulation of human factors, such as sleep recovery, psychological recovery, and physical recovery processes. There is a lack of linkage between personnel status data, environmental data, and task performance data, which leads to biases in the simulation of current working conditions and performance evaluation of confined spaces. Summary of the Invention

[0004] In view of this, the present invention proposes a working condition simulation analysis method and system oriented towards human-machine-environment coupling.

[0005] The technical solution of this invention is implemented as follows: The first aspect of this invention provides a working condition simulation analysis method oriented towards human-machine-environment coupling, comprising: The confined space to be simulated is modeled and divided into multiple functional area modules; the functional area modules include a work area module, a living area module, a public area module, and a service area module. In each of the aforementioned functional area modules, corresponding environmental disturbance simulations and task simulations are performed to obtain feedback data for executing various types of tasks. The types of disturbances in the environmental disturbance simulation include lighting disturbances, noise disturbances, vibration disturbances, and gas disturbances. The feedback data includes behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task. The feedback data is subjectively and objectively weighted using the analytic hierarchy process (AHP) and entropy weighting method to obtain corresponding contribution indices. Based on the current collection configuration of each contribution index, corresponding data quality deduction items and coupling impact quantities are determined. Combined with the contribution indices, the operational efficiency status, recovery status, and risk status of the tested object are determined. The coupling impact quantity is related to the degree of coupling between environmental load and personnel response load. Based on the operational efficiency status, the recovery status, and the risk status, an adjustment strategy is generated to adjust the environmental parameters or setting parameters of each functional area module.

[0006] Based on the above technical solutions, preferably, the step of performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks includes: In the residential area module, the lighting environment required for sleep recovery or circadian rhythm adjustment is created by adjusting the illuminance, color temperature, duration of light exposure, and start and end times of light exposure. Sleep recovery or circadian rhythm recovery tests were conducted in the aforementioned lighting environment to obtain corresponding feedback data.

[0007] Based on the above technical solutions, preferably, the step of performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks includes: In the public area module, the visual environment for psychological recovery evaluation is created by adjusting the area color mode, lighting color temperature, and illuminance. Psychological recovery tests were conducted in the visual environment to obtain corresponding feedback data.

[0008] Based on the above technical solutions, preferably, the step of performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks includes: In the service area module, the temperature and humidity environment required for physical recovery is created by adjusting the exercise load and air conditioning temperature and humidity conditions; Physical recovery tests were conducted in the specified temperature and humidity environment to obtain corresponding feedback data.

[0009] Based on the above technical solutions, preferably, the behavioral state data includes eye movement behavior indicators and facial expression indicators; the eye movement behavior indicators include effective gaze ratio, pupil diameter, pupil diameter change, blink frequency, and blink duration; the facial expression indicators include negative expression ratio, neutral expression ratio, positive expression ratio, and number of expression fluctuations. The physiological data include heart rate, electrocardiogram characteristics, respiratory rate, blood oxygen saturation, body temperature, and blood pressure. The cognitive self-assessment data includes reaction time, accuracy, attention level, memory level, and cognitive load; The task performance data includes reaction time, accuracy, false negative rate, false positive rate, task completion time, and task completion status in alert response tasks, N-back tasks, or operational judgment tasks. The environmental adaptation data includes illuminance, color temperature, noise level, vibration frequency, vibration acceleration, temperature, humidity, carbon dioxide concentration, and volatile organic compound concentration. The control log data includes data missing rate, equipment interruption flag, environmental parameter exceeding limit flag, manual stop flag, or linkage control abnormality flag.

[0010] Based on the above technical solutions, preferably, the step of determining the corresponding data quality deduction item and coupling impact based on the current collection configuration of each contribution index includes: Based on the current collection configuration of each contribution index, the weights are redistributed in stages to obtain the staged weights and data quality deduction items corresponding to different task stages; the data quality deduction items represent the comprehensive penalty score caused by data defects such as failure to collect indicators, collection failure, and equipment interruption. The contribution index is weighted using the staged weights to obtain the environmental load and the personnel response load, and the coupling influence is determined based on the environmental load and the personnel response load.

[0011] Based on the above technical solutions, preferably, the step of generating adjustment strategies based on the operational efficiency status, the recovery status, and the risk status to adjust the environmental parameters or setting parameters of each functional area module includes: When at least one of the operational performance state, the recovery state, and the risk state meets the preset triggering conditions, a task adjustment strategy, a state adjustment strategy, an environment adjustment strategy, a recovery adjustment strategy, a data adjustment strategy, and a safety adjustment strategy are generated to adjust the current regional environmental parameters, the target recovery area, the recovery mode, the collected data, the platform equipment, and / or the safety protection process.

[0012] Furthermore, a second aspect of the present invention provides a working condition simulation and analysis system oriented towards human-machine-environment coupling, comprising: a functional partitioning module, a simulation feedback module, an index acquisition module, and a strategy generation module; wherein, The functional zoning module is configured to simulate and model the confined space to be simulated, and divide it into multiple functional area modules; the functional area modules include a work area module, a living area module, a public area module, and a service area module; The simulation feedback module is configured to perform corresponding environmental disturbance simulation and task simulation in each of the functional area modules, and obtain feedback data for executing various types of tasks; the disturbance types in the environmental disturbance simulation include lighting disturbance, noise disturbance, vibration disturbance, and gas disturbance; the feedback data includes the behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task. The index acquisition module is configured to use the analytic hierarchy process (AHP) and entropy weighting method to subjectively and objectively weight the feedback data to obtain corresponding contribution indices; based on the current collection configuration of each contribution index, it determines the corresponding data quality deduction item and coupling impact quantity, and combines the contribution indices to determine the operational efficiency status, recovery status, and risk status of the tested object; the coupling impact quantity is related to the degree of coupling between environmental load and personnel reaction load; The strategy generation module is configured to generate adjustment strategies based on the operation performance status, the recovery status, and the risk status, so as to adjust the environmental parameters or setting parameters of each functional area module.

[0013] More preferably, a third aspect of the present invention provides an electronic device, including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the human-machine-environment coupling-oriented working condition simulation analysis method described in the first aspect.

[0014] More preferably, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the working condition simulation analysis method oriented towards human-machine-environment coupling described in the first aspect.

[0015] The working condition simulation analysis method and system of the present invention, which is oriented towards human-machine-environment coupling, has the following advantages over the prior art: 1. By uniformly dividing the confined space into four functional modules—work, living, public, and service—corresponding to scenarios such as work, sleep rhythm recovery, psychological relaxation, and physical training recovery, the system simultaneously conducts simulations of various environmental disturbances, including lighting, noise, vibration, and gas. This comprehensively covers the entire process of human factors activities during work and the entire recovery cycle. It can simultaneously simulate the three key human factors recovery processes of sleep, psychology, and physical fitness, achieving linkage simulation between workload and multi-dimensional recovery processes. This closely matches the real activity patterns of people staying in confined spaces for extended periods. It fully binds environmental disturbances, task execution, personnel's physical and mental state, and equipment operation information, realizing human-machine-environment linkage. This greatly improves the accuracy and reliability of space operation simulation and performance evaluation.

[0016] 2. The contribution index of each indicator is calculated by combining the analytic hierarchy process (AHP) and the entropy weight method. This approach relies on human factors expertise and utilizes the distribution characteristics of the experimental data to objectively allocate indicator weights, avoiding evaluation bias caused by single weighting. Furthermore, it introduces dual correction factors, such as data quality deduction items and the influence of environment-personnel coupling, to quantify the loss of assessment credibility caused by missing indicators and data collection failures, as well as the coupled negative impact of the superposition of environmental and human loads. This corrects the assessment distortion caused by simply superimposing indicators, accurately quantifies the coupling effect of human-machine-environment, significantly improves the accuracy of closed space working condition simulation and personnel performance assessment, and reduces assessment bias.

[0017] 3. Based on the calculated work efficiency status, recovery status, and risk status of personnel, the system automatically generates environmental and task setting adjustment strategies for each functional area. It can specifically adjust disturbance parameters such as lighting, noise, vibration, and gas in each area, as well as task configurations, forming a closed-loop system from multi-zone simulation acquisition and multi-source data fusion evaluation to full-domain linkage control. It can dynamically optimize work conditions and adjust the sleep, psychological, and physical recovery environment as needed, providing automated and dynamic optimization methods for the preliminary verification of solutions in confined spaces. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a working condition simulation analysis method oriented towards human-machine-environment coupling provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a working condition simulation and analysis system oriented towards human-machine-environment coupling, provided by an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a working condition simulation analysis method oriented towards human-machine-environment coupling provided by an embodiment of the present invention; the working condition simulation analysis method oriented towards human-machine-environment coupling provided by the present invention includes: S110 simulates and models the confined space to be simulated, and divides it into multiple functional area modules; the functional area modules include work area module, living area module, public area module and service area module.

[0022] S120 performs corresponding environmental disturbance simulations and task simulations in each functional area module to obtain feedback data for executing various types of tasks. The types of disturbances in the environmental disturbance simulation include lighting disturbances, noise disturbances, vibration disturbances, and gas disturbances. The feedback data includes the behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task.

[0023] S130 uses the analytic hierarchy process (AHP) and entropy weighting method to subjectively and objectively weight the feedback data to obtain the corresponding contribution indices. Based on the current collection configuration of each contribution index, the corresponding data quality deduction items and coupling impact quantities are determined. Combined with the contribution indices, the operational efficiency status, recovery status, and risk status of the tested object are determined. The coupling impact quantity is related to the degree of coupling between environmental load and personnel response load.

[0024] S140 generates adjustment strategies based on operational efficiency status, recovery status, and risk status to adjust the environmental parameters or setting parameters of each functional area module.

[0025] In this embodiment, the work area module is used to construct the working conditions for task execution and to simulate and record the subjects' work behavior, work performance, and environmental exposure during task execution. The living area module is used to construct a rhythmic lighting and sleep recovery environment and to intervene in the subjects' sleep recovery process. The public area module is used to construct a psychological recovery environment and to provide subjects with sensory stimulation interventions such as visual and auditory stimulation. The service area module is used to construct a sports training and physical recovery environment and to adjust the exercise load for subjects.

[0026] Based on the experimental objectives, a task script can be established to specify the order in which participants enter different areas, the environmental parameters for each area, the task duration, the data collection method, and the triggering conditions. The task script consists of several task phases, each represented as follows:

[0027] ; in, This represents the k-th task phase. This indicates the operating area corresponding to this stage. This indicates the combination of environmental parameters for this stage. Indicates the duration of the task. This indicates the data types that need to be collected in this stage. This indicates the triggering condition for the end or switching of this phase.

[0028] Following the task script, each area is sequentially controlled to enter its corresponding operational state, allowing participants to complete task execution, recovery intervention, or state adjustment in different areas. In the work area, environmental parameters such as lighting, noise, vibration, air quality, and pollutant concentration can be adjusted according to the task script; in the residential area, the light environment can be adjusted according to the rhythmic lighting script; in the public area, color, lighting, and sound environment modes can be switched according to psychological recovery goals; in the service area, exercise load, temperature, and humidity can be controlled to create corresponding physical recovery conditions. Within each task phase, environmental conditions, personnel status, and task performance are collected synchronously, and the collected data is correlated with participant, task, work area, task phase, and time information to form a phased data record that can be used for subsequent effectiveness evaluation. The participant's work effectiveness, recovery status, and risk status in the current task phase are evaluated, generating a state evaluation result for that phase. Based on this, it is determined whether the platform needs to trigger parameter adjustments for recovery intervention or safety control.

[0029] In some embodiments, corresponding environmental disturbance simulations and task simulations are performed in each functional area module to obtain feedback data on the execution of various types of tasks, including: In the residential area module, the lighting environment required for sleep recovery or circadian rhythm adjustment is created by adjusting the illuminance, color temperature, duration of light exposure, and start and end times of light exposure. Conduct sleep recovery or circadian rhythm recovery tests in a light-filled environment and obtain corresponding feedback data.

[0030] In this embodiment, a rhythmic lighting recovery script is set up within the residential area. The script includes lighting color temperature, illuminance, illumination duration, start and end times, and a sleep or alertness test schedule to create a visual recovery environment related to sleep recovery or rhythm adjustment. During the residential area recovery phase, the relationship between light dose, duration of action, and recovery effect can be evaluated using sleep monitoring data, subjective sleep assessments, alertness test results, or measured light environment data.

[0031] In some embodiments, corresponding environmental disturbance simulations and task simulations are performed in each functional area module to obtain feedback data on the execution of various types of tasks, including: In the public area module, the visual environment for psychological recovery evaluation is created by adjusting the area color mode, lighting color temperature, and illuminance. Conduct psychological recovery tests in a visual environment and obtain corresponding feedback data.

[0032] In this embodiment, a psychological recovery script is set up within the public area. The script includes the area's color mode, lighting color temperature, illuminance, lighting duration, dwell time, and the time points for collecting data from self-assessment scales or cognitive tests. The platform links the subject's comfort scores, emotional state scores, psychological stress scores, cognitive test results, or changes in dwell time before and after entering the public area with the public area's color and lighting parameters to demonstrate the impact of different visual environments on comfort, emotional state, and the degree of psychological recovery.

[0033] In some embodiments, corresponding environmental disturbance simulations and task simulations are performed in each functional area module to obtain feedback data on the execution of various types of tasks, including: In the service area module, the temperature and humidity conditions required for physical recovery are created by adjusting the exercise load and air conditioning temperature and humidity. Physical recovery tests were conducted in a temperature and humidity environment to obtain corresponding feedback data.

[0034] In this embodiment, exercise training and physical recovery scripts are set up within the service area. These scripts include exercise type, exercise load level, exercise duration, recovery interval, temperature, humidity, and physiological safety thresholds. The platform links exercise load, temperature, and humidity conditions with heart rate changes, post-exercise recovery heart rate, blood oxygen saturation, respiratory rate, and subjective fatigue score. When heart rate, blood oxygen saturation, or subjective fatigue score reaches a preset safety threshold, the exercise load is reduced or the recovery interval is extended. When recovery heart rate, subjective fatigue score, or physiological arousal level does not reach the target range, the exercise load, temperature, or humidity conditions are adjusted to balance the risks associated with physical recovery, physiological arousal, and physiological load.

[0035] It should be noted that a work condition simulation task script is set up within the work area. The work condition simulation task script includes the task type, task sequence, environmental disturbance methods, task duration, data acquisition type, and phase termination conditions. Task types include alertness response tasks, N-back tasks, or operational judgment tasks. Environmental disturbance methods include disturbances in lighting color temperature and illuminance, noise level, vibration frequency or acceleration, and air quality or pollutant concentration. Participants complete cognitive, operational, or collaborative tasks under predetermined environmental conditions.

[0036] In some embodiments, behavioral state data includes eye movement behavior indicators and facial expression indicators; eye movement behavior indicators include effective gaze ratio, pupil diameter, pupil diameter change, blink frequency, and blink duration; facial expression indicators include negative expression ratio, neutral expression ratio, positive expression ratio, and number of expression fluctuations. Physiological data include heart rate, electrocardiographic characteristics, respiratory rate, blood oxygen saturation, body temperature, and blood pressure; Cognitive self-assessment data include reaction time, accuracy, attention level, memory level, and cognitive load; Task performance data includes reaction time, accuracy, false negative rate, false positive rate, task completion time, and task completion status in alert response tasks, N-back tasks, or operational judgment tasks. Environmental adaptation data includes illuminance, color temperature, noise level, vibration frequency, vibration acceleration, temperature, humidity, carbon dioxide concentration, and volatile organic compound concentration. Control log data includes data missing rate, equipment interruption flag, environmental parameter exceeding limit flag, manual stop flag, or linkage control abnormality flag.

[0037] In this embodiment, the feedback data is categorized according to the data source and the current evaluation object, as shown below: ; in, For task performance data, For physiological state data, For behavioral state data, To understand self-assessment data, Data adapted to the environment, To control log data.

[0038] Task performance indicators This includes reaction time, accuracy, false negative rate, misreport rate, task completion time, and task completion status in alertness response tasks, N-back tasks, or performance judgment tasks. For alertness response tasks and N-back tasks, raw data includes trial number, task type, stimulus presentation time, reaction time, key press response, and accuracy marker. Physiological state data is also included. This includes heart rate, electrocardiogram (ECG) characteristics, respiratory rate, blood oxygen saturation, body temperature, and blood pressure; among which, ECG characteristics are obtained by extracting the R-peak interval from the ECG sampling sequence.

[0039] The feedback data is bound to the task stages to form staged data records, which can be specifically represented as follows: ; in, Indicates the subject's number. This represents the k-th task script stage. Represents a timestamp. This represents measured environmental data. This represents data on the physiological state of individuals. Represents behavioral state data. This represents cognitive test or psychological self-assessment data. This represents task performance data. This indicates platform control log data.

[0040] In some embodiments, the corresponding data quality deduction items and coupling impact quantities are determined based on the current collection configuration of each contribution index, including: Based on the current collection configuration of each contribution index, the weights are redistributed in stages to obtain the stage weights and data quality deduction items corresponding to different task stages; the data quality deduction items represent the comprehensive penalty scores caused by data defects such as failure to collect indicators, collection failure, and equipment interruption. The contribution index is weighted using staged weights to obtain environmental load and human response load, and the coupling impact is determined based on the environmental load and human response load.

[0041] In this embodiment, when task performance data When the current task phase is enabled and the data is valid, for the alertness response task, calculate the average reaction time and accuracy for the current phase, as shown below: ; in, For the reaction time of the i-th alertness response task trial, For correctness marking, n is the number of trials. To accurately reflect the number of trials, This is an indicator function.

[0042] For the N-back task, the N-back accuracy, target reaction time, false negative rate, and false positive rate for the current stage are calculated as follows: ; Where m is the number of N-back trials. To effectively and accurately reflect the number of trials, The number of times the target stimulus did not respond. This represents the number of false responses to non-target stimuli.

[0043] When physiological state data When the current task phase is enabled and the data is valid, for ECG data, extract the R-peak time series and calculate the RR interval, mean heart rate, and heart rate variability, as shown below: ; in, Let i be the time corresponding to the i-th R peak. This refers to the period between adjacent R peaks. Instantaneous heart rate, This is an indicator of heart rate variability.

[0044] When behavioral status data When eye-tracking devices are enabled and data acquisition is valid during the current task phase, the effective gaze ratio, average pupil diameter, blink frequency, and average blink duration are calculated for the eye-tracking data, as shown below: ; in, To determine the effective number of eye-tracking sampling points, This represents the total number of eye-tracking sampling points. For the effective pupil diameter, For the number of blinking events, The duration of a single blink. This represents the duration of the current phase.

[0045] When behavioral status data When facial recognition devices are enabled and the collected data is valid during the current task phase, the proportion of negative expressions and the number of expression fluctuations in the current phase are calculated for facial expression data, as shown below: ; in, The cumulative duration of negative expressions during the current phase. For effective facial recognition duration, Let i be the emotion category of the i-th facial recognition segment. The number of effective facial recognition segments.

[0046] For feedback data with individual differences, baseline or low-load phase data from the same participant before the task were used as a benchmark, and the baseline correction values ​​are shown below: ; in, Let j be the measured value of the j-th indicator in the k-th stage. The baseline value for the corresponding indicator for the same subject. Let be the baseline correction scale value of the j-th index, and The baseline correction scale value is determined by the index configuration table before the start of the evaluation task and remains fixed in the same evaluation task.

[0047] For positive indicators, standardization is performed according to the following formula: ; For negative indicators, standardization is performed according to the following formula: ; For target interval indicators, standardization is performed according to the following formula: ; in, and These are the lower and upper limits of the j-th indicator, respectively. To allow deviation from width, For standardized dimensionless indicators, This means that the calculation result will be limited to between 0 and 1.

[0048] Establish an indicator hierarchy based on the evaluation objects of the current task phase, and obtain subjective weights through the analytic hierarchy process. The analytic hierarchy process (AHP) includes constructing a judgment matrix, calculating the weight vector corresponding to the largest eigenvalue of the judgment matrix, and performing a consistency check.

[0049] Entropy weight is calculated based on standardized indicators from samples of the same task type or the same task stage. As shown below: ; in, Let j be the proportion of the j-th indicator in the r-th sample. For information entropy, Here, is the coefficient of difference, n is the sample size, and m is the number of indicators; Combining the subjective weight and the entropy weight, the comprehensive weight is obtained as follows: ; in, The subjective and objective weighting adjustment coefficient has a value range of 0.5 to 0.7.

[0050] For the current task phase, based on the enabled flag and valid markers The overall weights are redistributed in stages, as shown below: ; And calculate the data quality deductions: ; in, The stage-based weight of the j-th effective indicator in the k-th stage. This is a deduction item for data quality; it occurs when the metric is not configured in the task script. This indicator is not included in the current stage calculation and does not result in data quality deduction; when the indicator has been configured but data collection is invalid, This indicator is not included in the weighting of effective indicators, and is calculated according to its overall weight. Included in data quality deductions .

[0051] The environmental load is calculated based on the degree of exceeding or deviating from the environmental adaptation indicators that are enabled and valid in the current task script, as shown below: ; Based on the current task script, activate and collect valid task performance data. Physiological state data Behavioral status data Cognitive self-assessment data The degree of adverse change is used to calculate the personnel response load, as shown below: ; in, For environment adaptation data The extracted q-th environmental risk indicator, For task performance data Physiological state data Behavioral status data Cognitive self-assessment data The extracted risk index and behavioral status data of the p-th person's response were obtained. The eye movement behavior indicators and facial expression indicators were converted into risk indicators of personnel response according to the indicator direction. and These are the weights of the environmental risk assessment indicators and the personnel response risk assessment indicators for the kth stage, respectively. The weights of indicators that are not activated in the current task stage or whose data are invalid are 0.

[0052] The degree of coupling and the magnitude of coupling impact are calculated based on environmental load and human response load, as shown below: ; in, This indicates the degree of coupling between environmental load and human response load. This represents the coupling effect used for state index correction. The coupling effect increases when both environmental load and human response load increase simultaneously.

[0053] Based on the phased weighting, the contribution values ​​for task performance, physiological state, behavioral state, cognitive self-rating, and environmental adaptation are calculated separately, as shown below: ; in, and These are the contribution values ​​for task performance, physiological state, behavioral state, cognitive self-evaluation, and environmental adaptation.

[0054] When a set of metrics is not enabled by the task script in the current task phase, the platform does not calculate the contribution value of that set of metrics. When a set of metrics has been enabled by the task script but the proportion of valid data is lower than a preset validity threshold, the platform marks that set of metrics as invalid for the current phase and records it in the platform's operation log or data quality metric set. Record data quality markers.

[0055] When the current stage is the work area task stage, the index for calculating the job efficiency status is as follows: ; When the current stage is the recovery stage, the index for calculating the recovery status is as follows: ; in, This is a set of recovery evaluation metrics configured by the task script and for which data is valid during the current recovery phase. The beneficial improvement after recovery relative to before recovery is shown below: ; For all task phases, the risk status index is calculated as follows: ; in, This is a set of risk indicators configured by the task script and with valid data in the current stage. Risk status indicators, dimensionless indicators, are derived from environmental, physiological, behavioral, cognitive self-assessment, task performance, or platform logs. The corresponding risk indicator is . For coupling correction coefficients, The two factors are used as data quality deduction coefficients. After being determined based on the calibration samples, they are written into the evaluation task configuration table and kept fixed in the same evaluation task.

[0056] Coupling correction coefficient and data quality deduction factor The method for determining the coefficients is as follows: using the results of the manual state annotation of the calibration samples as a reference, in the candidate coefficient set... and The coefficient combination that maximizes the consistency between the state determination result and the manual state labeling result is selected; when manual state labeling results are unavailable, the coupling influence is considered. and data quality deductions The maximum permissible percentage of influence in the state index is determined.

[0057] Before determining the status, the operational efficiency status threshold, recovery status threshold, and risk status threshold are determined based on the calibration samples. Let... This represents the c-th percentile. This represents the set of operational efficiency indices for a normal operational calibration sample. This represents the set of recovery indices for samples that have reached the standard for recovery. The set of risk indices representing the normal state calibration samples is shown below:

[0058] ; in, The threshold for operational efficiency status. To restore the state threshold, This is the risk status threshold. The threshold is set as the safety termination threshold. When manual state labeling results are available, each state threshold is corrected in the corresponding candidate threshold set to ensure that the consistency rate between the state determination result and the manual state labeling result meets the preset requirements.

[0059] When the current stage is the work area task stage, and When, it is judged as a normal state; when When, it is determined to be a state requiring intervention; when When the current stage is the recovery stage, it is judged as a risky state. When, it is determined to be restored to the standard status; when When, it is determined to continue the recovery state; when When this occurs, it is determined to be a risky situation.

[0060] The phase status assessment results should include at least the current task phase number, operating area, evaluation window, percentage of valid data, and operational efficiency status index. Recovery Status Index Risk Status Index Environmental load Personnel response load Coupling influence Key abnormal indicators, status determination results, and subsequent linkage control recommendations.

[0061] In some embodiments, adjustment strategies are generated based on operational performance status, recovery status, and risk status to adjust environmental parameters or setting parameters of each functional area module, including: When at least one of the operational performance status, recovery status, and risk status meets the preset triggering conditions, a task adjustment strategy, a status adjustment strategy, an environmental adjustment strategy, a recovery adjustment strategy, a data adjustment strategy, and a safety adjustment strategy are generated to adjust the current regional environmental parameters, target recovery area, recovery mode, collected data, platform equipment, and / or safety protection processes.

[0062] In this embodiment, the triggering conditions include at least one of the following: the current task phase reaches the preset duration or completion condition; the subject is in a state requiring intervention, a state of continued recovery, or a state of risk; the environmental measured data exceeds the range allowed by the task script; the recovery phase does not meet the preset recovery requirements; key data is missing, the acquisition equipment is interrupted, or the data cannot correspond to the current task phase; the subject shows obvious discomfort, environmental parameters exceed the safety threshold, key equipment is abnormal, or the experiment is manually stopped by the experimenter.

[0063] Trigger types include: task triggers for generating suggestions for the next stage after the current stage ends; status triggers for generating recovery suggestions based on the individual status of the subjects, such as physiological, psychological, and performance status; environment triggers for adjusting environmental parameters such as lighting, noise, vibration, temperature, humidity, and gas concentration; recovery triggers for adjusting recovery parameters or extending the recovery process when the recovery effect does not meet the standard; data triggers for marking abnormal data; and safety triggers for implementing safety controls during the experiment.

[0064] The intervention targets include current regional environmental parameters, target recovery area, recovery mode, collected data, platform equipment, and security protection processes.

[0065] In some embodiments, please refer to Figure 2 , Figure 2 This is a schematic diagram of a working condition simulation and analysis system oriented towards human-machine-environment coupling, provided by an embodiment of the present invention. The present invention provides a working condition simulation and analysis system 200 oriented towards human-machine-environment coupling, comprising: a functional partitioning module 210, a simulation feedback module 220, an index acquisition module 230, and a strategy generation module 240.

[0066] The functional zoning module 210 is configured to perform simulation modeling of the enclosed and confined space to be simulated and divide it into multiple functional area modules; the functional area modules include a work area module, a residential area module, a public area module, and a service area module.

[0067] The simulation feedback module 220 is configured to perform corresponding environmental disturbance simulations and task simulations in each functional area module to obtain feedback data for executing various types of tasks. The types of disturbances in the environmental disturbance simulation include lighting disturbances, noise disturbances, vibration disturbances, and gas disturbances. The feedback data includes the behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task.

[0068] The index acquisition module 230 is configured to use the analytic hierarchy process (AHP) and entropy weighting method to subjectively and objectively weight the feedback data to obtain the corresponding contribution index; based on the current collection configuration of each contribution index, the corresponding data quality deduction item and coupling impact quantity are determined, and combined with the contribution index, the operational efficiency status, recovery status and risk status of the tested object are determined; the coupling impact quantity is related to the degree of coupling between environmental load and personnel response load.

[0069] The strategy generation module 240 is configured to generate adjustment strategies based on the operational performance status, recovery status, and risk status, so as to adjust the environmental parameters or setting parameters of each functional area module.

[0070] In some embodiments, the analog feedback module 220 is specifically configured as follows: In the residential area module, the lighting environment required for sleep recovery or circadian rhythm adjustment is created by adjusting the illuminance, color temperature, duration of light exposure, and start and end times of light exposure. Conduct sleep recovery or circadian rhythm recovery tests in a light-filled environment and obtain corresponding feedback data.

[0071] In some embodiments, the analog feedback module 220 is specifically configured as follows: In the public area module, the visual environment for psychological recovery evaluation is created by adjusting the area color mode, lighting color temperature, and illuminance. Conduct psychological recovery tests in a visual environment and obtain corresponding feedback data.

[0072] In some embodiments, the analog feedback module 220 is specifically configured as follows: In the service area module, the temperature and humidity conditions required for physical recovery are created by adjusting the exercise load and air conditioning temperature and humidity. Physical recovery tests were conducted in a temperature and humidity environment to obtain corresponding feedback data.

[0073] In some embodiments, behavioral state data includes eye movement behavior indicators and facial expression indicators; eye movement behavior indicators include effective gaze ratio, pupil diameter, pupil diameter change, blink frequency, and blink duration; facial expression indicators include negative expression ratio, neutral expression ratio, positive expression ratio, and number of expression fluctuations. Physiological data include heart rate, electrocardiographic characteristics, respiratory rate, blood oxygen saturation, body temperature, and blood pressure; Cognitive self-assessment data include reaction time, accuracy, attention level, memory level, and cognitive load; Task performance data includes reaction time, accuracy, false negative rate, false positive rate, task completion time, and task completion status in alert response tasks, N-back tasks, or operational judgment tasks. Environmental adaptation data includes illuminance, color temperature, noise level, vibration frequency, vibration acceleration, temperature, humidity, carbon dioxide concentration, and volatile organic compound concentration. Control log data includes data missing rate, equipment interruption flag, environmental parameter exceeding limit flag, manual stop flag, or linkage control abnormality flag.

[0074] In some embodiments, the index acquisition module 230 is specifically configured as follows: Based on the current collection configuration of each contribution index, the weights are redistributed in stages to obtain the stage weights and data quality deduction items corresponding to different task stages; the data quality deduction items represent the comprehensive penalty scores caused by data defects such as failure to collect indicators, collection failure, and equipment interruption. The contribution index is weighted using staged weights to obtain environmental load and human response load, and the coupling impact is determined based on the environmental load and human response load.

[0075] In some embodiments, the policy generation module 240 is specifically configured as follows: When at least one of the operational performance status, recovery status, and risk status meets the preset triggering conditions, a task adjustment strategy, a status adjustment strategy, an environmental adjustment strategy, a recovery adjustment strategy, a data adjustment strategy, and a safety adjustment strategy are generated to adjust the current regional environmental parameters, target recovery area, recovery mode, collected data, platform equipment, and / or safety protection processes.

[0076] It should be noted that the working condition simulation analysis system oriented towards human-machine-environment coupling provided in this application embodiment and the working condition simulation analysis method oriented towards human-machine-environment coupling provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned working condition simulation analysis method oriented towards human-machine-environment coupling, and the repeated parts will not be described again.

[0077] In some embodiments, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 provided in this embodiment includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program, when executed by the processor, implements the aforementioned human-machine-environment coupling-oriented working condition simulation analysis method.

[0078] Specifically, processor 310 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 310 may also include onboard memory for caching purposes. Processor 310 may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0079] The memory 320 may be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, the memory 320 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, apparatuses, or propagation media. Specific examples of the memory 320 include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and may also be random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0080] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, this program implements the aforementioned human-machine-environment coupling-oriented work condition simulation analysis method. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0081] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0082] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by the equivalents of the appended claims. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A working condition simulation analysis method oriented towards human-machine-environment coupling, characterized in that, include: The confined space to be simulated is modeled and divided into multiple functional area modules; the functional area modules include a work area module, a living area module, a public area module, and a service area module. In each of the aforementioned functional area modules, corresponding environmental disturbance simulations and task simulations are performed to obtain feedback data for executing various types of tasks. The types of disturbances in the environmental disturbance simulation include lighting disturbances, noise disturbances, vibration disturbances, and gas disturbances. The feedback data includes behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task. The feedback data is subjectively and objectively weighted using the analytic hierarchy process (AHP) and entropy weighting method to obtain corresponding contribution indices. Based on the current collection configuration of each contribution index, corresponding data quality deduction items and coupling impact quantities are determined. Combined with the contribution indices, the operational efficiency status, recovery status, and risk status of the tested object are determined. The coupling impact quantity is related to the degree of coupling between environmental load and personnel response load. Based on the operational efficiency status, the recovery status, and the risk status, an adjustment strategy is generated to adjust the environmental parameters or setting parameters of each functional area module.

2. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The process involves performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks, including: In the residential area module, the lighting environment required for sleep recovery or circadian rhythm adjustment is created by adjusting the illuminance, color temperature, duration of light exposure, and start and end times of light exposure. Sleep recovery or circadian rhythm recovery tests were conducted in the aforementioned lighting environment to obtain corresponding feedback data.

3. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The process involves performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks, including: In the public area module, the visual environment for psychological recovery evaluation is created by adjusting the area color mode, lighting color temperature, and illuminance. Psychological recovery tests were conducted in the visual environment to obtain corresponding feedback data.

4. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The process involves performing corresponding environmental disturbance simulations and task simulations in each of the functional area modules to obtain feedback data for executing various types of tasks, including: In the service area module, the temperature and humidity environment required for physical recovery is created by adjusting the exercise load and air conditioning temperature and humidity conditions; Physical recovery tests were conducted in the specified temperature and humidity environment to obtain corresponding feedback data.

5. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The behavioral status data includes eye movement behavior indicators and facial expression indicators; the eye movement behavior indicators include effective gaze ratio, pupil diameter, pupil diameter change, blink frequency, and blink duration; The facial expression indicators include the proportion of negative expressions, the proportion of neutral expressions, the proportion of positive expressions, and the number of expression fluctuations; The physiological data include heart rate, electrocardiogram characteristics, respiratory rate, blood oxygen saturation, body temperature, and blood pressure. The cognitive self-assessment data includes reaction time, accuracy, attention level, memory level, and cognitive load; The task performance data includes reaction time, accuracy, false negative rate, false positive rate, task completion time, and task completion status in alert response tasks, N-back tasks, or operational judgment tasks. The environmental adaptation data includes illuminance, color temperature, noise level, vibration frequency, vibration acceleration, temperature, humidity, carbon dioxide concentration, and volatile organic compound concentration. The control log data includes data missing rate, equipment interruption flag, environmental parameter exceeding limit flag, manual stop flag, or linkage control abnormality flag.

6. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The determination of the corresponding data quality deduction items and coupling impact quantities based on the current collection configuration of each contribution index includes: Based on the current collection configuration of each contribution index, the weights are redistributed in stages to obtain the staged weights and data quality deduction items corresponding to different task stages; the data quality deduction items represent the comprehensive penalty score caused by data defects such as failure to collect indicators, collection failure, and equipment interruption. The contribution index is weighted using the staged weights to obtain the environmental load and the personnel response load, and the coupling influence is determined based on the environmental load and the personnel response load.

7. The working condition simulation analysis method for human-machine-environment coupling as described in claim 1, characterized in that, The method of generating adjustment strategies based on the operational efficiency status, the recovery status, and the risk status to adjust the environmental parameters or setting parameters of each functional area module includes: When at least one of the operational performance state, the recovery state, and the risk state meets the preset triggering conditions, a task adjustment strategy, a state adjustment strategy, an environment adjustment strategy, a recovery adjustment strategy, a data adjustment strategy, and a safety adjustment strategy are generated to adjust the current regional environmental parameters, the target recovery area, the recovery mode, the collected data, the platform equipment, and / or the safety protection process.

8. A working condition simulation and analysis system oriented towards human-machine-environment coupling, characterized in that, include: The system includes a functional partitioning module, a simulation feedback module, an index acquisition module, and a strategy generation module; among them... The functional zoning module is configured to perform simulation modeling of the confined space to be simulated and divide it into multiple functional area modules; the functional area modules include a work area module, a living area module, a public area module, and a service area module; The simulation feedback module is configured to perform corresponding environmental disturbance simulation and task simulation in each of the functional area modules, and obtain feedback data for executing various types of tasks; the disturbance types in the environmental disturbance simulation include lighting disturbance, noise disturbance, vibration disturbance, and gas disturbance; the feedback data includes the behavioral state data, physiological state data, cognitive self-evaluation data of the test subject, as well as task performance data, environmental adaptation data, and control log data related to the task. The index acquisition module is configured to use the analytic hierarchy process (AHP) and entropy weighting method to subjectively and objectively weight the feedback data to obtain corresponding contribution indices; based on the current collection configuration of each contribution index, it determines the corresponding data quality deduction item and coupling impact quantity, and combines the contribution indices to determine the operational efficiency status, recovery status, and risk status of the tested object; the coupling impact quantity is related to the degree of coupling between environmental load and personnel reaction load; The strategy generation module is configured to generate adjustment strategies based on the operation performance status, the recovery status, and the risk status, so as to adjust the environmental parameters or setting parameters of each functional area module.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the working condition simulation analysis method oriented towards human-machine-environment coupling as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the working condition simulation analysis method for human-machine-environment coupling as described in any one of claims 1 to 7.

Images