Civil aviation pilot psychological competency evaluation method and system fused with biological feedback

Abstract

The invention relates to the field of pilot psychological competency evaluation, and discloses a civil aviation pilot psychological competency evaluation method and system fused with biofeedback, and the method comprises the following steps: S1, collecting the physiological data and behavior data of a pilot in a baseline test situation, and building individualized psychological load baseline data; s2, in the virtual situation, collecting multi-modal data, including physiological data and behavior data, of the pilot in real time; S3, analyzing the data collected in real time through a multi-modal data fusion model, and generating a psychological state score of the pilot; s4, providing real-time feedback and situation difficulty adjustment based on the psychological state score; and S5, generating a personalized psychological competency assessment report. The psychological state analysis of multi-modal data fusion is matched with the real-time physiological data acquisition, so that the dynamic monitoring and accurate evaluation effects on the psychological load of the pilot are realized, and the defect that the psychological state of the pilot is difficult to dynamically capture in real time in the prior art is overcome.

Description

Technical Field

[0001] The present invention relates to the field of pilot psychological competence assessment, and in particular to a method and system for assessing the psychological competence of civil aviation pilots by integrating biofeedback. Background Art

[0002] The psychological competence of civil aviation pilots is an important factor in ensuring flight safety and the physical and mental health of pilots. In a high-pressure, complex and emergency-prone flight environment, pilots not only need to have professional skills, but also must have a stable psychological quality to adapt to various emergency situations. Through effective assessment of pilots' psychological competence, their psychological adaptability can be identified, helping airlines screen and train suitable pilots to ensure flight safety.

[0003] Existing technologies mainly assess pilots’ psychological competence through psychological questionnaires, cognitive tests and basic physiological measurements. For example, standardized psychological questionnaires are used to assess pilots’ emotional state and stress level; cognitive tests are used to measure their attention and reaction speed; in addition, some assessment systems monitor pilots’ physiological indicators such as heart rate and skin conductivity to reflect their stress response to a certain extent.

[0004] However, existing technologies have obvious deficiencies in real-time and situational adaptability. Traditional static assessment methods are difficult to capture the ever-changing psychological state of pilots in real flight missions. In addition, a single psychological questionnaire and basic physiological data often cannot accurately reflect the dynamic changes in psychological load, and the lack of situational assessment methods limits the accuracy and reliability of the assessment results. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method and system for evaluating the psychological competence of civil aviation pilots incorporating biofeedback, which solves the problem in the prior art that psychological questionnaires and basic physiological data are often difficult to accurately reflect the dynamic changes in psychological load and lack contextualized evaluation methods, which limits the accuracy and reliability of the evaluation results.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for evaluating the psychological competence of civil aviation pilots integrating biofeedback, comprising the following steps: S1. Collect the pilot's physiological and behavioral data in the baseline test scenario to establish individualized psychological workload baseline data; S2. Collect multimodal data of pilots in real time in virtual situations, including physiological and behavioral data; S3, analyzing the real-time collected data through a multimodal data fusion model to generate a pilot's psychological state score; S4, based on the psychological state score, provide real-time feedback and situation difficulty adjustment; S5. Generate personalized psychological competency assessment reports and provide early warnings when psychological load exceeds individual thresholds.

[0007] Preferably, the physiological data is collected by a sensor device, and the sensor includes: ECG sensor, used to collect pilots’ heart rate variability data; Galvanic skin response sensors, which monitor changes in skin conductivity; Brain wave sensor, used to collect brain wave signals.

[0008] Preferably, the multimodal data fusion comprises the following steps: a. Extract heart rate variability, skin galvanic response, and brain wave features from physiological data; b. Extract gaze time, gaze frequency and operation reaction time features from behavioral data; c. Use a multimodal deep learning model to fuse and analyze physiological and behavioral characteristics to generate a real-time psychological state score for the pilot.

[0009] Preferably, the heart rate variability is calculated by the following formula:

[0010] in, For the heartbeat interval, For interval The average value of The number of heartbeats.

[0011] Preferably, the skin electrical response characteristic is calculated by the following formula:

[0012] in, is the change in conductivity, that is, the difference between the current conductivity and the previous conductivity, It is the change in time, that is, the time interval between measurement points.

[0013] Preferably, the establishment of the personalized mental workload baseline data comprises the following steps: (a) Collect the pilot's heart rate variability in a baseline situation; (b) setting an individualized mental workload threshold based on the mean and standard deviation of the heart rate variability to satisfy the following relationship:

[0014] in, It represents the average value of heart rate variability, that is, the mean HRV value of the pilot in the baseline test situation. The mean HRV value is an important indicator for evaluating the activity of the individual autonomic nervous system and reflects the heart rate fluctuation characteristics of the pilot in a normal state. It represents the standard deviation of HRV, that is, the fluctuation range of HRV value. This value reflects the normal range of heart rate variability of an individual under baseline conditions. Represents the adjustment factor, which is used to control the sensitivity of the threshold.

[0015] A civil aviation pilot psychological competency assessment system integrating biofeedback, the system comprising: Data collection module, used to collect pilots' physiological and behavioral data; Data fusion analysis module, used to fuse the collected data and generate psychological state scores; A virtual situational testing module is used to generate a situational virtual testing environment; A real-time feedback module is used to provide feedback information based on the psychological state score; Personalized psychological competency assessment module, used to generate personalized psychological competency assessment reports; The early warning module is used to provide an early warning when it is detected that the mental load exceeds the individual threshold.

[0016] Preferably, the data fusion analysis module is composed of the following sensors: An electrocardiogram sensor is attached to the pilot's chest and is used to collect the pilot's heart rate variability; A galvanic skin response sensor, which is worn on the pilot's wrist and is used to monitor changes in skin conductivity; The brain wave sensor is fixed to the pilot's head and is used to detect the pilot's brain wave signals.

[0017] Preferably, the virtual situation test module includes a situation difficulty adaptive adjustment module for dynamically adjusting the task difficulty of the virtual situation based on the real-time psychological state of the pilot, and reducing the task difficulty of the virtual situation when the psychological load level of the pilot exceeds the individual threshold.

[0018] Preferably, the personalized psychological competency assessment module is used to: Generates emotion management scores based on brainwaves and galvanic skin response; Generate a mental workload score based on heart rate variability and operating behavior; Generate teamwork scores and decision-making scores based on behavioral data in team situations; The warning module generates a warning when detecting that the psychological state score is lower than the personalized psychological load threshold, and issues a prompt on the system interface to remind the pilot to adjust the psychological state in time.

[0019] The present invention provides a method and system for evaluating the psychological competence of civil aviation pilots by integrating biofeedback. It has the following beneficial effects: 1. The present invention realizes dynamic monitoring and accurate evaluation of pilots' psychological load through multimodal data fusion psychological state analysis combined with real-time physiological data collection, solving the problem of the existing technology that it is difficult to capture the pilots' psychological state in real time and dynamically.

[0020] 2. The present invention realizes the accurate evaluation of the pilot's psychological state in various situations through the situational design of the virtual situation test module and the adaptive adjustment of the situation difficulty, making the evaluation closer to the actual flight environment and enhancing the authenticity and situational adaptability of the evaluation.

[0021] 3. The present invention achieves an immediate warning effect on the pilot's overload status by setting a personalized psychological load threshold in conjunction with the automatic warning function, which helps to promptly detect and intervene in pilots with excessive psychological load and support them in psychological self-regulation and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Embodiment 1: Please see attached Figure 1The embodiment of the present invention provides a method for evaluating the psychological competence of civil aviation pilots by integrating biofeedback, comprising the following steps: S1, collecting the pilot's physiological data and behavioral data in a baseline test scenario to establish individualized psychological load baseline data; S2, collecting the pilot's multimodal data in real time in a virtual scenario, including physiological data and behavioral data; S3, analyzing the real-time collected data through a multimodal data fusion model to generate a pilot's psychological state score; S4, providing real-time feedback and situation difficulty adjustment based on the psychological state score; S5, generating a personalized psychological competence assessment report, and providing an early warning when the psychological load exceeds the individual threshold.

[0025] In the present invention, firstly, the pilot's physiological data and behavioral data are collected in a baseline test scenario to establish their individualized psychological load baseline data. The establishment of baseline data is an important link to ensure the accuracy of the assessment. By recording the pilot's heart rate variability, skin conductivity, brain waves and other physiological signals, as well as eye movement, reaction speed and other behavioral data under no task load or standard tasks, the personalized threshold of their physiological and psychological state is formed, which provides a reference for the psychological load analysis in the subsequent virtual scenario, so that the system can accurately identify abnormal states according to the unique physiological response pattern of each pilot, and judge whether they are under excessive psychological load; In the actual virtual situation test, the multimodal data of the pilot, including physiological data and behavioral data, is collected in real time through a variety of sensors to fully capture the emotional fluctuations and stress changes of the pilot during the execution of the simulated mission. Through the analysis of the multimodal data fusion model, the system can comprehensively process the real-time collected data and generate a psychological state score for the pilot. The score not only reflects the pilot's psychological load in the current situation, but also includes key psychological indicators such as emotional regulation and attention distribution. Based on the psychological state score, the system will provide real-time feedback to the pilot and adjust the difficulty of the virtual situation in a timely manner according to the dynamic changes of the score, so that the test environment is closer to the actual flight mission scenario. At the same time, the system will generate a personalized psychological competency assessment report to help managers understand the psychological adaptability characteristics of pilots more comprehensively. When the psychological load exceeds the individual threshold, the system will automatically issue an early warning to provide timely psychological health reminders for pilots and managers to prevent them from suffering excessive psychological pressure during the mission.

[0026] Physiological data is collected through sensor devices, including: ECG sensor, used to collect pilots’ heart rate variability data; Galvanic skin response sensors, which monitor changes in skin conductivity; Brain wave sensor, used to collect brain wave signals.

[0027] Multimodal data fusion includes the following steps: a. Extract heart rate variability, skin galvanic response, and brain wave features from physiological data; b. Extract gaze time, gaze frequency and operation reaction time features from behavioral data; c. Use a multimodal deep learning model to fuse and analyze physiological and behavioral characteristics to generate a real-time psychological state score for the pilot.

[0028] Heart rate variability is calculated using the following formula:

[0029] in, For the heartbeat interval, For interval The average value of The number of heartbeats.

[0030] The skin galvanic response characteristics are calculated by the following formula:

[0031] in, is the change in conductivity, that is, the difference between the current conductivity and the previous conductivity, It is the change in time, that is, the time interval between measurement points.

[0032] In the present invention, physiological data is collected through a variety of sensor devices to comprehensively and accurately monitor the psychological and physiological state of the pilot during the mission. First, the ECG sensor is used to collect heart rate variability (HRV) data. HRV can reflect the activity state of the autonomic nervous system and is an important indicator for measuring psychological load and stress level. By recording the changes in the time interval between each heartbeat of the pilot, the HRV data captured by the ECG sensor can effectively reflect the pilot's stress response and emotional fluctuations. Secondly, the galvanic skin response (EDA) sensor is used to monitor changes in skin conductivity. Changes in conductivity are often accompanied by emotional fluctuations, especially in anxiety and tension. Skin conductivity will increase, so EDA data can be used to track the pilot's emotions and stress response. In addition, the electroencephalogram (EEG) sensor is used to collect the pilot's brain activity signals. By detecting the characteristics of brain waves in different frequency bands, the pilot's concentration and cognitive load level can be analyzed. At this time, a multi-dimensional physiological information foundation is formed to ensure that the system can fully and dynamically understand the pilot's psychological state; In the process of multimodal data fusion, the system first extracts heart rate variability, galvanic skin response, and brain wave features from physiological data to analyze the pilot's physiological response pattern during the mission. In addition, features such as gaze time, gaze frequency, and operation reaction time are extracted from behavioral data to capture the pilot's behavioral performance and changes in concentration. After preprocessing, these feature data are input into the multimodal deep learning model for fusion analysis. By comprehensively considering physiological and behavioral data, the system generates a real-time psychological state score. This score can dynamically and accurately reflect the pilot's psychological load, emotional fluctuations, and concentration state. Based on this score, the system can monitor the pilot's psychological state in real time and identify potential high-load or stressful situations, thereby providing pilots and managers with immediate psychological state feedback and suggestions, and supporting pilots' psychological management and self-regulation during missions.

[0033] The establishment of personalized mental workload baseline data includes the following steps: (a) Collect the pilot's heart rate variability in a baseline situation; (b) Based on the mean and standard deviation of heart rate variability, set an individualized mental workload threshold to satisfy the following relationship:

[0034] in, It represents the average value of heart rate variability, that is, the mean HRV value of the pilot in the baseline test situation. The mean HRV value is an important indicator for evaluating the activity of the individual autonomic nervous system and reflects the heart rate fluctuation characteristics of the pilot in a normal state. It represents the standard deviation of HRV, that is, the fluctuation range of HRV value. This value reflects the normal range of heart rate variability of an individual under baseline conditions. Represents the adjustment factor, which is used to control the sensitivity of the threshold.

[0035] In the present invention, the basic data of the pilot's physiological response is formed by collecting heart rate variability (HRV) in a baseline situation. In the baseline situation, the pilot is in a standard state of relatively low pressure, which can truly reflect his normal psychological and physiological reactions. By collecting heart rate variability data, the activity of the pilot's autonomic nervous system in a quiet and relaxed state can be observed, thereby obtaining the individual HRV mean. This mean is an important indicator for evaluating the activity of the autonomic nervous system, and can show the physiological stability of the pilot without task pressure. The psychological load baseline data formed by this mean provides a reference point for subsequent psychological load assessments under different task intensities, allowing the system to perform a more personalized analysis of the pilot's psychological load state; After the baseline data collection is completed, the system will set an individualized psychological load threshold based on the pilot's HRV mean and standard deviation. The HRV standard deviation characterizes the fluctuation amplitude of the individual's heart rate variability in the baseline situation, and reflects the natural fluctuation range of the heart rate without task pressure. By combining the HRV mean and standard deviation, a reasonable threshold range for psychological load can be determined. When the pilot's HRV data during the mission exceeds this range, it indicates that he may be in a state of psychological overload or tension. In order to enhance the flexibility of the threshold, the adjustment coefficient is used to control the sensitivity of the threshold to adapt to the differences in physiological characteristics of different individuals. The evaluation system can more accurately identify the pilot's psychological load under different task intensities, and issue a warning in time when the individual threshold is exceeded, supporting the pilot's psychological self-regulation and management during the mission.

[0036] Embodiment 2: Please see attached Figure 2 , the above system comprises: Data collection module, used to collect pilots' physiological and behavioral data; Data fusion analysis module, used to fuse the collected data and generate psychological state scores; A virtual situational testing module is used to generate a situational virtual testing environment; A real-time feedback module is used to provide feedback information based on the psychological state score; Personalized psychological competency assessment module, used to generate personalized psychological competency assessment reports; The early warning module is used to provide an early warning when it is detected that the mental load exceeds the individual threshold.

[0037] The system of the present invention includes multiple modules for ensuring comprehensive and dynamic evaluation and feedback of the pilot's psychological state.

[0038] First, the data acquisition module is used to collect the pilot's physiological and behavioral data. Through devices such as electrocardiogram sensors, galvanic skin response sensors, and brain wave sensors, the system can obtain the pilot's heart rate variability, skin conductivity, brain waves and other physiological indicators in real time. At the same time, behavioral data is collected through devices such as eye trackers and somatosensory sensors to record the pilot's gaze pattern, reaction time and other information, providing comprehensive data support for subsequent analysis; Secondly, the data fusion analysis module fuses the collected multimodal data, analyzes the physiological and behavioral data through a deep learning model, and generates a pilot's psychological state score. This score can comprehensively reflect the pilot's current psychological load level, emotional state, and concentration, providing a basis for real-time feedback and situational adjustment; The virtual scenario test module is used to create a highly simulated flight mission environment. It uses virtual reality technology to build a variety of test scenarios, such as routine flights and emergencies, so as to observe the pilot's psychological state and behavioral performance in different scenarios. The system provides scenario changes according to test requirements, thereby increasing the authenticity and situational effect of psychological state assessment; The real-time feedback module provides pilots with instant feedback based on their psychological state scores. When the psychological load reaches a certain level, the system will use visual prompts or audio guidance to remind pilots to take deep breaths, concentrate, and so on, in order to relieve psychological pressure and emotional fluctuations. This feedback mechanism helps pilots to self-regulate during the test; In addition, the personalized psychological competence assessment module is used to generate a personalized psychological competence assessment report. Based on the pilot's physiological and behavioral performance in different situations, the report evaluates his psychological adaptability and load tolerance by comparing it with his individual baseline data, and provides scores such as emotion management, psychological load and decision-making ability to help airlines conduct a comprehensive assessment of the pilot's psychological competence; Finally, the warning module issues a warning when the pilot's psychological load exceeds the individual threshold. When the psychological state score shows that the pilot's stress state is close to or exceeds the personalized threshold, a warning message will appear on the system interface to remind pilots and managers to pay attention to their mental health and make appropriate adjustments to prevent potential psychological overload risks.

[0039] The data fusion analysis module consists of the following sensors: ECG sensor: The ECG sensor is attached to the pilot's chest to collect the pilot's heart rate variability; Galvanic skin response sensor, which is worn on the pilot's wrist to monitor changes in skin conductivity; Brain wave sensor: The brain wave sensor is fixed on the pilot's head and is used to detect the pilot's brain wave signals.

[0040] The virtual situation test module includes a situation difficulty adaptive adjustment module, which is used to dynamically adjust the task difficulty of the virtual situation based on the pilot's real-time psychological state. When the pilot's psychological load level exceeds the individual threshold, the task difficulty of the virtual situation is reduced.

[0041] The Personalized Psychological Competency Assessment Module is used to: Generates emotion management scores based on brainwaves and galvanic skin response; Generate a mental workload score based on heart rate variability and operating behavior; Generate teamwork scores and decision-making scores based on behavioral data in team situations; The early warning module generates an early warning when it detects that the psychological state score is lower than the personalized psychological load threshold, and issues a prompt on the system interface to remind the pilot to adjust his psychological state in time.

[0042] In the present invention, the heart rate variability (HRV) data is collected by the ECG sensor. The galvanic skin response (EDA) sensor monitors the change of skin conductivity. The electroencephalogram (EEG) sensor detects the brain wave signal. The virtual situation test module includes a situation difficulty adaptive adjustment module. Through real-time psychological state data, the system can dynamically adjust the task difficulty of the virtual situation. When the pilot's psychological load level exceeds the individual threshold, the system automatically reduces the task difficulty to reduce the pilot's stress burden. At the same time, the personalized psychological competency assessment module generates a detailed psychological competency score based on the analysis results of multimodal data, including the following aspects: Emotional management score: Based on the data of brain waves and skin electrical response, the pilots' ability to regulate emotions during the mission is scored to reflect the stability of their emotional management; Mental stress score: Combined with heart rate variability and operational behavior data, it evaluates the pilot's mental load tolerance and reflects his or her stress tolerance during the mission; Teamwork and Decision-making Score: Based on behavioral data in team situations, the pilot's teamwork and decision-making abilities are assessed to reflect their performance in a collaborative environment; The warning module is used to automatically generate a warning when the psychological state score is lower than the personalized psychological load threshold. When the system detects that the pilot's psychological load exceeds the safe range, the system interface will issue a prompt to remind the pilot to adjust his psychological state in time to prevent psychological pressure from having a negative impact on his flight performance and mental health. Through this timely warning mechanism, the system can effectively help pilots maintain a good psychological state, thereby improving flight safety.

[0043] A personalized psychological state log can be generated for each pilot, and these logs are recorded to form a personal psychological profile in the system database. The log contains detailed records of the pilot's physiological data, psychological state scores, emotional fluctuations, task performance, etc. during tests and actual tasks, and is used to track the pilot's psychological adaptability, stress tolerance, and emotional management capabilities over the long term. By recording and accumulating logs, the system can not only reflect the pilot's psychological state in real time, but also provide detailed data support for subsequent training; Specifically, after each test or flight mission, the system automatically stores the pilot's multimodal data and analysis results in a personal log. The log content includes: Physiological data recording: including heart rate variability (HRV), galvanic skin response (EDA), electroencephalogram (EEG) and other data, which are used to analyze the pilot's physiological load and emotional response; Mental State Score: A mental state score generated based on real-time data fusion analysis, reflecting the pilot's mental workload level, concentration, and emotional stability at a specific mission stage; Situational performance and task performance: including behavioral data such as operation reaction time, gaze time, error rate, etc. in virtual situations to reflect their performance in different stressful situations; The system automatically captures and records the pilot's physiological and behavioral data during each test, and generates a detailed log upon completion. The log contains information such as timestamps, the pilot's current mental state, and real-time feedback from the system. Through this refined logging, managers can clearly understand the changes in the pilot's mental state and observe the mood and stress fluctuations in different mission situations. The log can be summarized by time period such as day, week or month, making it easier for managers to monitor the long-term mental health of pilots.

[0044] After a certain number of log records have been accumulated, the system can conduct in-depth analysis based on the pilot's individual data to identify his or her psychological strengths and weaknesses in specific situations or task types. By analyzing these data, the system can help develop personalized psychological training plans. For example, the system can analyze that a pilot has large emotional fluctuations in a high-stress situation, and can provide him or her with more stress management and emotional regulation training in subsequent training. The system can also use the accumulated log data to identify psychological state patterns and coping characteristics through machine learning algorithms, and further optimize the training content to make it more suitable for the actual needs of individuals. Ultimately, personalized training based on log data can significantly improve the pilot's psychological competence and enhance his or her adaptability and stability in actual tasks. The system's log recording and analysis mechanism not only provides reliable data support for personalized training, but also forms a long-term system for pilot psychological health management, ensuring that pilots can maintain a good mental state in different mission scenarios.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The method for evaluating the psychological competence of civil aviation pilots by integrating biofeedback is characterized by: The following steps are involved: S1. Collect the pilot's physiological and behavioral data in the baseline test scenario to establish individualized psychological workload baseline data; S2. Collect multimodal data of pilots in real time in virtual situations, including physiological and behavioral data; S3, analyzing the real-time collected data through a multimodal data fusion model to generate a pilot's psychological state score; S4, based on the psychological state score, provide real-time feedback and situation difficulty adjustment; S5. Generate personalized psychological competency assessment reports and provide early warnings when psychological load exceeds individual thresholds.

2. The method for evaluating the psychological competence of civil aviation pilots integrating biofeedback according to claim 1 is characterized in that: The physiological data is collected by a sensor device, and the sensor includes: ECG sensor, used to collect pilots’ heart rate variability data; Galvanic skin response sensors, which monitor changes in skin conductivity; Brain wave sensor, used to collect brain wave signals.

3. The method for evaluating the psychological competence of civil aviation pilots integrating biofeedback according to claim 1, characterized in that: The multimodal data fusion comprises the following steps: a. Extract heart rate variability, skin galvanic response, and brain wave features from physiological data; b. Extract gaze time, gaze frequency and operation reaction time features from behavioral data; c. Use a multimodal deep learning model to fuse and analyze physiological and behavioral characteristics to generate a real-time psychological state score for the pilot.

4. The method for evaluating the psychological competence of civil aviation pilots integrating biofeedback according to claim 3 is characterized in that: The heart rate variability is calculated by the following formula: in, For the heartbeat interval, For interval The average value of The number of heartbeats.

5. The method for evaluating the psychological competence of civil aviation pilots integrating biofeedback according to claim 3 is characterized in that: The skin electrical response characteristics are calculated by the following formula: in, is the change in conductivity, that is, the difference between the current conductivity and the previous conductivity, It is the change in time, that is, the time interval between measurement points.

6. The method for evaluating the psychological competence of civil aviation pilots integrating biofeedback according to claim 3 is characterized in that: The establishment of the personalized mental workload baseline data comprises the following steps: (a) Collect the pilot's heart rate variability in a baseline situation; (b) setting an individualized mental workload threshold based on the mean and standard deviation of the heart rate variability to satisfy the following relationship: in, It represents the average value of heart rate variability, that is, the mean HRV value of the pilot in the baseline test situation. The mean HRV value is an important indicator for evaluating the activity of the individual autonomic nervous system and reflects the heart rate fluctuation characteristics of the pilot in a normal state. It represents the standard deviation of HRV, that is, the fluctuation range of HRV value. This value reflects the normal range of heart rate variability of an individual under baseline conditions. Represents the adjustment factor, which is used to control the sensitivity of the threshold.

7. A civil aviation pilot psychological competence assessment system integrating biofeedback, based on a civil aviation pilot psychological competence assessment method integrating biofeedback according to any one of claims 1 to 6, characterized in that: The system comprises: Data collection module, used to collect pilots' physiological and behavioral data; Data fusion analysis module, used to fuse the collected data and generate psychological state scores; A virtual situational testing module is used to generate a situational virtual testing environment; A real-time feedback module is used to provide feedback information based on the psychological state score; Personalized psychological competency assessment module, used to generate personalized psychological competency assessment reports; The early warning module is used to provide an early warning when it is detected that the mental load exceeds the individual threshold.

8. The civil aviation pilot psychological competency assessment system integrating biofeedback according to claim 7, characterized in that: The data fusion analysis module is composed of the following sensors: An electrocardiogram sensor is attached to the pilot's chest and is used to collect the pilot's heart rate variability; A galvanic skin response sensor, which is worn on the pilot's wrist and is used to monitor changes in skin conductivity; The brain wave sensor is fixed to the pilot's head and is used to detect the pilot's brain wave signals.

9. The civil aviation pilot psychological competency assessment system integrating biofeedback according to claim 7, characterized in that: The virtual situation test module includes a situation difficulty adaptive adjustment module, which is used to dynamically adjust the task difficulty of the virtual situation based on the real-time psychological state of the pilot, and reduce the task difficulty of the virtual situation when the psychological load level of the pilot exceeds the individual threshold.

10. The civil aviation pilot psychological competency assessment system integrating biofeedback according to claim 8, characterized in that: The Personalized Psychological Competency Assessment Module is used to: Generates emotion management scores based on brainwaves and galvanic skin response; Generate a mental workload score based on heart rate variability and operating behavior; Generate teamwork scores and decision-making scores based on behavioral data in team situations; The warning module generates a warning when detecting that the psychological state score is lower than the personalized psychological load threshold, and issues a prompt on the system interface to remind the pilot to adjust the psychological state in time.

Images