A method and system for evaluating the psychological competence of civil aviation crew members by integrating biofeedback

Abstract

The invention discloses a method and system for evaluating the psychological competence of civil aviation flight attendants by integrating biofeedback, which relates to the field of professional evaluation of civil aviation flight attendants and comprises the following steps: a) setting evaluation indicators for the psychological competence of civil aviation flight attendants, wherein the evaluation indicators are determined based on psychological principles and the professional characteristics of flight attendants; b) collecting psychological data of the flight attendants under evaluation, and preprocessing the collected psychological data; the method and system for evaluating the psychological competence of civil aviation flight attendants by integrating biofeedback integrates psychological data and physiological index data, extracts key features by using a deep learning algorithm, constructs a psychological load evaluation model, and realizes real-time evaluation of the psychological load changes of the flight attendants under evaluation in a simulation task. At the same time, combined with the psychological competence evaluation results, comparison and verification are performed, and the psychological competence level of the flight attendants under evaluation is comprehensively evaluated, thereby improving the comprehensiveness and accuracy of the evaluation results.

Description

Technical Field

[0001] The present invention relates to a civil aviation flight attendant occupation assessment technology, and in particular to a civil aviation flight attendant psychological competence assessment method and system integrating biofeedback. Background Art

[0002] In the field of civil aviation flight attendants, psychological competence is a key indicator for assessing whether flight attendants have the psychological qualities required to perform flight missions. Traditional psychological competence assessment methods often rely on tools such as questionnaires, interview records, and psychological testing software. Although these methods can reflect the psychological qualities of the testees to a certain extent, they often lack real-time, dynamic, and personalized performance. At the same time, most of these methods ignore the physiological response data of the testees in simulated tasks, which can often more directly and accurately reflect the psychological load and psychological state of the testees.

[0003] In recent years, with the continuous development of biofeedback technology, more and more researchers have begun to try to apply biofeedback technology to the field of psychological assessment. Biofeedback technology can accurately reflect the psychological state and psychological load changes of the measured person in real time by collecting the physiological index data of the measured person (such as heart rate, blood pressure, skin conductance, etc.). However, there are still few studies on the application of biofeedback technology to the psychological competency assessment of civil aviation flight attendants, and most of them remain in the stage of theoretical discussion and preliminary trial, and have not yet formed a complete and systematic assessment method and system. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for evaluating the psychological competence of civil aviation crew members incorporating biofeedback, so as to solve the problem that traditional psychological competence evaluation methods in the prior art often rely on tools such as questionnaires, interview records and psychological testing software. Although these methods can reflect the psychological quality of the tested persons to a certain extent, they often lack real-time, dynamic and personalized performance. Most of these methods ignore the physiological response data of the tested persons in simulated tasks, resulting in technical problems such as difficulty in directly and accurately reflecting the psychological load and psychological state of the tested persons.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for evaluating the psychological competence of civil aviation crew members integrating biofeedback, comprising the following steps:

[0006] a) Set up assessment indicators for the psychological competence of civil aviation flight attendants, which are determined based on psychological principles and the professional characteristics of flight attendants;

[0007] b) Collect the psychological data of the flight attendants being tested during the assessment and pre-process the collected psychological data;

[0008] c) Based on machine learning algorithms, the pre-processed psychological data is trained to generate dynamic weights for each evaluation indicator;

[0009] d) While the flight attendants are performing the psychological assessment task, the physiological index data of the flight attendants are collected synchronously using biofeedback technology;

[0010] e) Fuse psychological data with physiological index data, extract key features using deep learning algorithms, build a psychological load assessment model, and evaluate the changes in psychological load of the tested person in the simulation task in real time;

[0011] f) Compare and verify the psychological load assessment results with the psychological competency assessment results, and combine them with dynamic weights to generate a comprehensive psychological competency assessment report for the flight attendants.

[0012] Furthermore, the psychological data acquisition method in step b) includes one or more of questionnaire survey results, interview records and results output by psychological testing software.

[0013] Furthermore, the physiological indicator data in step d) includes at least one of heart rate, blood pressure and skin conductance.

[0014] Furthermore, the weight adjustment in step c) is based on one or more of the performance of the person being assessed, historical assessment data, and industry standards.

[0015] Furthermore, the deep learning algorithm in step e) includes a convolutional neural network or a recurrent neural network, which is used to fuse the psychological data with the physiological indicator data, extract key features, and construct a psychological load assessment model.

[0016] A civil aviation crew psychological competence assessment system integrating biofeedback is also provided, which is applicable to the civil aviation crew psychological competence assessment method integrating biofeedback described above, and includes: an assessment index setting module, a psychological data collection module, a dynamic weight generation module, a physiological index data collection module, a psychological load assessment model construction module and a comprehensive assessment report generation module;

[0017] The evaluation index setting module is used to set the evaluation index of civil aviation flight attendants' psychological competence. The evaluation index is determined based on the principles of psychology and the professional characteristics of flight attendants.

[0018] The psychological data collection module is used to collect the psychological reaction data of the flight attendants being tested during the assessment;

[0019] The dynamic weight generation module trains the preprocessed psychological data based on the machine learning algorithm to generate the dynamic weights of each evaluation indicator;

[0020] The physiological index data collection module is used to collect the physiological index data of the flight attendants while the flight attendants are performing the psychological assessment task;

[0021] The psychological load assessment model building module is used to integrate psychological data with physiological index data, build a psychological load assessment model, and evaluate the changes in the psychological load of the tested person in the simulation task in real time;

[0022] The comprehensive assessment report generation module is used to compare and verify the psychological load assessment results with the psychological competence assessment results, and generate a comprehensive psychological competence assessment report for the tested flight attendants in combination with dynamic weights.

[0023] Furthermore, the model building module uses at least one of the weighted average method, the hierarchical analysis method or the fuzzy comprehensive evaluation method to normalize and standardize the psychological data to build a psychological competency assessment model.

[0024] Furthermore, the physiological data acquisition module includes at least one of a heart rate monitoring submodule, a blood pressure monitoring submodule and a skin conductance monitoring submodule, wherein the heart rate monitoring submodule is used to collect the heart rate of the measured flight attendant, the blood pressure monitoring submodule is used to collect the blood pressure of the measured flight attendant, and the skin conductance monitoring submodule is used to collect the skin conductance data of the measured flight attendant.

[0025] Furthermore, the dynamic weight generation module also includes a weight adjustment algorithm, which dynamically adjusts the weight of each evaluation indicator according to the real-time performance of the person being tested in the simulation task and the historical evaluation data. The weight adjustment algorithm is specifically as follows:

[0026] Assume the initial weight vector is w0=(w1,w2,…,w n ), where n is the number of evaluation indicators; collect new psychological data X new =(x1, x2,…, x m ), where x i is the psychological reaction data vector of the person being tested during the assessment, and m is the number of psychological reaction data; according to the performance of the person being tested during the assessment, the score of each indicator is calculated as s = (s1, s2, ..., s n ), calculate the product of the score and the initial weight, and get the preliminary evaluation result S i =s·w0;

[0027] According to the comparison between the preliminary evaluation results and the actual performance of the simulation task, the weights are adjusted and the performance adjustment function f is introduced. p (s,w0,α), this function adjusts the weight according to the score s, the initial weight w0 and the performance adjustment coefficient α, and the adjusted weight is w p , w p =fp (s,w0,α), Where α is the performance adjustment factor, is the average score, σ s is the standard deviation of the scores;

[0028] According to the historical evaluation data H=(h1,h2,…,h k ), where h j Represents the data of the jth historical evaluation, and calculates the historical trend of each indicator t=(t1, t2, …, t n ), introduce the trend adjustment function f t (t,w p ,β), the adjusted weight w t =f t (t,w p ,β),w t,i =w p,i ·(1+β·t i ), where β is the trend adjustment coefficient;

[0029] Normalize the adjusted weights to ensure that the sum of the weights is 1. The normalized weight vector w f =(w 1,f ,w 2,f ,…,w n,f ), calculated by the following formula: Output the adjusted weight vector w f .

[0030] Furthermore, the comprehensive evaluation report generation module includes:

[0031] A data integration unit, used to receive and integrate data from the psychological data collection module, the physiological index data collection module and the dynamic weight generation module;

[0032] The comparison and verification unit is used to compare and verify the psychological load assessment results output by the psychological load assessment module with the psychological competency assessment results output by the psychological competency assessment module to ensure the consistency and relevance between the two.

[0033] The comprehensive evaluation unit, based on the comparison and verification results and the dynamic weights provided by the dynamic weight generation module, performs weighted summation on each evaluation index to obtain the comprehensive psychological competence score of the tested flight attendant;

[0034] The report generation unit generates a comprehensive psychological competency assessment report containing scores, strengths, weaknesses and personalized suggestions based on the comprehensive assessment results. The report is output in the form of electronic or paper documents for review and use by the tested flight attendants, airline management and training personnel.

[0035] Compared with the prior art, the present invention provides a method and system for evaluating the psychological competence of civil aviation flight attendants by integrating biofeedback. By integrating psychological data and physiological index data, using a deep learning algorithm to extract key features, and constructing a psychological load evaluation model, the present invention realizes real-time evaluation of the changes in the psychological load of the flight attendants being tested in the simulated tasks. At the same time, combined with the results of the psychological competence evaluation, comparison and verification are performed to comprehensively evaluate the psychological competence level of the tested personnel, thereby improving the comprehensiveness and accuracy of the evaluation results.

[0036] By adopting a dynamic weight generation module, the weight of each evaluation indicator is dynamically adjusted according to the performance of the person being evaluated, historical evaluation data and industry standards. This dynamic adjustment mechanism can more flexibly adapt to the individual differences of different flight attendants and ensure that the evaluation results can truly reflect the actual psychological competence level of each person being evaluated;

[0037] The evaluation method and system of the present invention improve the objectivity and accuracy of the evaluation results and enhance the credibility of the evaluation system by introducing biofeedback technology and a dynamic weight adjustment mechanism. At the same time, by generating a comprehensive evaluation report and establishing a feedback mechanism, the evaluation system is made more practical and effective, providing a more reliable basis for the selection, training and career development of flight attendants. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0039] Figure 1 A schematic flow chart of a method for evaluating the psychological competence of civil aviation crew members integrating biofeedback provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0041] Embodiment 1:

[0042] See also Figure 1 , a method for evaluating the psychological competence of civil aviation crew members integrating biofeedback, comprising the following steps:

[0043] a) Set up assessment indicators for the psychological competence of civil aviation flight attendants, which are determined based on psychological principles and the professional characteristics of flight attendants;

[0044] Based on the principles of psychology and the professional characteristics of flight attendants, and according to the results of the questionnaire survey, the psychological competence evaluation indicators of civil aviation flight attendants mainly include the following aspects:

[0045] Emotional stability: assesses whether flight attendants can remain calm and rational when faced with stress and challenges;

[0046] Stress resistance: examines whether flight attendants can maintain work efficiency and accuracy under high-pressure environments;

[0047] Emergency response ability: Tests whether flight attendants can quickly make correct judgments and take correct actions in emergency situations;

[0048] Teamwork skills: Evaluate the flight attendants’ communication and collaboration skills with colleagues and passengers;

[0049] Service awareness: examine whether the flight attendants have the awareness and ability to provide high-quality services to passengers;

[0050] b) Collect the psychological data of the flight attendants being tested during the assessment and pre-process the collected psychological data, which specifically includes removing outliers and missing values ​​and standardizing or normalizing the data to ensure the accuracy and reliability of the data;

[0051] c) Based on machine learning algorithms, the preprocessed psychological data is trained to generate dynamic weights of each evaluation indicator. The preprocessed psychological data is used as input and trained using machine learning algorithms (such as support vector machines, random forests, etc.) to generate dynamic weights of each evaluation indicator;

[0052] d) While the flight attendants are performing the psychological assessment task, the physiological index data of the flight attendants are collected synchronously using biofeedback technology. The physiological index data can objectively reflect the physiological response of the flight attendants in a specific situation, thus providing us with a more comprehensive basis for psychological load assessment;

[0053] e) Fuse psychological data with physiological index data, extract key features using deep learning algorithms, build a psychological load assessment model, and evaluate the changes in psychological load of the tested person in the simulation task in real time;

[0054] The specific steps are as follows:

[0055] Clean the psychological data and physiological indicator data to remove outliers and missing values;

[0056] Standardize or normalize the data to ensure the consistency of data from different sources in terms of dimensions;

[0057] Using feature concatenation, feature selection or feature dimensionality reduction methods, psychological data and physiological index data are integrated into a unified feature vector; in order to reduce computational complexity and improve model performance, the dimensionality reduction techniques of principal component analysis (PCA) or linear discriminant analysis (LDA) can be used to reduce the number of features;

[0058] Select a deep learning model (such as convolutional neural network CNN, recurrent neural network RNN, long short-term memory network LSTM, etc.), and train it according to the fused feature vector. Through the training process of the deep learning model, extract the key features that have an important impact on the psychological load assessment. The key features of psychological data: emotional stability index, attention allocation index, decision-making speed and quality; the key features of physiological indicators: heart rate (HR), heart rate variability (HRV), skin conductance (GSR), and electroencephalogram (EEG); fuse the psychological data and physiological indicators to form a fusion index, such as the psychological-physiological stress index. When using the deep learning algorithm for training, the key features that have an important impact on the psychological load assessment will be automatically extracted from the fused feature vector. These features are a combination or transformation of the above-mentioned key features of psychological data, key features of physiological indicators, and fusion features, which can more accurately reflect the psychological load state of the person being tested;

[0059] Using the extracted key features, a psychological workload assessment model is constructed. The model can evaluate the changes in the psychological workload of the subjects in the simulation task in real time. The psychological workload assessment model can be verified by cross-validation or holdout method to ensure its accuracy and reliability. According to the verification results, the model can be optimized to improve its assessment performance.

[0060] f) Compare and verify the results of psychological load assessment with the results of psychological competence assessment, and generate a comprehensive psychological competence assessment report of the tested flight attendants in combination with dynamic weights;

[0061] Compare the results of psychological workload assessment with those of psychological competency assessment, analyze the correlation and consistency between the two, and use correlation analysis or regression analysis to quantify the relationship between the two. Based on the results of the comparison and verification and combined with the actual performance of the subjects in the simulated tasks, dynamically adjust the weights of the psychological workload assessment results and psychological competency assessment results in the comprehensive assessment.

[0062] In one embodiment of the present invention, the deep learning algorithm in step e) includes a convolutional neural network (CNN) or a recurrent neural network (RNN), which is used to fuse psychological data with physiological indicator data, extract key features, and construct a psychological load assessment model.

[0063] In one embodiment of the present invention, the psychological data acquisition method in step b) includes one or more of questionnaire survey results, interview records and results output by psychological testing software.

[0064] In one embodiment of the present invention, the physiological indicator data in step d) includes at least one of heart rate, blood pressure and skin conductance.

[0065] In one embodiment of the present invention, the weight adjustment in step c) is based on one or more of the performance of the person being evaluated, historical evaluation data, and industry standards.

[0066] In one embodiment of the present invention, the deep learning algorithm in step e) includes a convolutional neural network (CNN) or a recurrent neural network (RNN), which is used to fuse the psychological data with the physiological index data, extract key features, and construct a psychological load assessment model;

[0067] This can be achieved by taking the following steps:

[0068] Use CNN to extract spatial features from physiological indicator data, such as the waveform characteristics of brain waves and the pattern of heart rate changes;

[0069] Use RNN to extract temporal dynamic features from time series data, such as the trend of heart rate changes, fluctuations in breathing rate, etc.;

[0070] For psychological data, text mining techniques can be used to extract features such as keywords and sentiment tendencies;

[0071] The features extracted from the psychological data and physiological index data are fused by feature concatenation or feature weighting to form a more comprehensive feature set;

[0072] Select a deep learning algorithm, such as CNN, RNN or its variants (such as LSTM, GRU, etc.), design parameters such as the number of network layers, number of neurons, activation function, etc. to build a suitable deep learning model, use the preprocessed data set to train the model, update the network parameters through the back propagation algorithm, and use cross-validation or early stopping strategies to prevent overfitting of the model during training. Use accuracy, recall rate, and F1 score to evaluate the performance of the model, and optimize the model based on the evaluation results. The optimization can be achieved by adjusting the network structure or adding data enhancement methods.

[0073] The trained deep learning model is applied to the actual task of psychological stress assessment of civil aviation flight attendants. By inputting new psychological data and physiological indicator data, the model can predict the psychological stress level of flight attendants.

[0074] The above method integrates psychological data and physiological indicator data, uses deep learning algorithms to extract key features, and constructs a psychological load assessment model. It realizes real-time assessment of the changes in psychological load of the tested flight attendants in simulated tasks, improves the accuracy and reliability of the assessment results, and dynamically adjusts the weight of each assessment indicator according to the performance of the tested personnel during the assessment, historical assessment data and industry standards. It can more flexibly adapt to the individual differences of different flight attendants and ensure that the assessment results can truly reflect the actual psychological competence level of each tested person.

[0075] Embodiment 2:

[0076] A civil aviation crew psychological competence assessment system integrating biofeedback, applicable to the above-mentioned civil aviation crew psychological competence assessment method integrating biofeedback, comprising: an assessment index setting module, a psychological data collection module, a dynamic weight generation module, a physiological index data collection module, a psychological load assessment model construction module and a comprehensive assessment report generation module;

[0077] The evaluation index setting module is used to set the evaluation index of civil aviation flight attendants' psychological competence. The evaluation index is determined based on the principles of psychology and the professional characteristics of flight attendants. The evaluation index covers the flight attendants' emotional stability, stress resistance, emergency response ability, teamwork ability and service awareness during work.

[0078] The psychological data collection module is used to collect the psychological reaction data of the flight attendants during the assessment. Through questionnaires, psychological tests, etc., the system can collect the psychological reaction data such as the psychological state and emotional changes of the flight attendants during the assessment;

[0079] The dynamic weight generation module trains the preprocessed psychological data based on the machine learning algorithm to generate the dynamic weights of each evaluation indicator;

[0080] The physiological index data collection module is used to collect the physiological index data of the flight attendants while they are performing the psychological assessment task. By collecting the physiological index data, the system can more comprehensively evaluate the psychological load and stress response ability of the flight attendants.

[0081] The psychological load assessment model building module is used to integrate psychological data with physiological index data, build a psychological load assessment model, and evaluate the changes in the psychological load of the tested personnel in the simulation task in real time. By building a psychological load assessment model, the system can timely discover problems such as excessive or insufficient psychological pressure of flight attendants, and take corresponding measures to intervene and adjust;

[0082] The comprehensive assessment report generation module is used to compare and verify the psychological load assessment results with the psychological competence assessment results, and generate a comprehensive psychological competence assessment report for the tested flight attendants in combination with dynamic weights.

[0083] Since flight attendants, as individuals, have differences in psychological quality, work experience, ability to cope with stress, etc., the importance of different evaluation indicators to different flight attendants will also be different. Therefore, by dynamically adjusting the weights, the system can more flexibly adapt to such individual differences and ensure that the evaluation results can truly reflect the actual psychological competence level of each flight attendant.

[0084] In one embodiment of the present invention, the model building module uses at least one of the weighted average method, the hierarchical analysis method or the fuzzy comprehensive evaluation method to normalize and standardize the psychological data to build a psychological competency assessment model.

[0085] In one embodiment of the present invention, the physiological data acquisition module includes at least one of a heart rate monitoring submodule, a blood pressure monitoring submodule and a skin conductance monitoring submodule, wherein the heart rate monitoring submodule is used to collect the heart rate of the measured flight attendant, the blood pressure monitoring submodule is used to collect the blood pressure of the measured flight attendant, and the skin conductance monitoring submodule is used to collect the skin conductance data of the measured flight attendant.

[0086] In one embodiment of the present invention, the dynamic weight generation module further includes a weight adjustment algorithm, which dynamically adjusts the weight of each evaluation indicator according to the real-time performance of the person being tested in the simulation task and historical evaluation data;

[0087] Since the importance of different evaluation indicators will vary for different flight attendants, and historical evaluation data records the flight attendants' past performance and growth trajectory, by dynamically adjusting the weights of each evaluation indicator based on the flight attendants' real-time performance and historical evaluation data, the flight attendants' future performance can be predicted more accurately. Dynamic adjustment of weights can reduce evaluation bias caused by fixed weight settings to ensure the accuracy and fairness of evaluation results, which helps to improve the credibility of the evaluation system and provide a more reliable basis for the selection, training and career development of flight attendants.

[0088] In one embodiment of the present invention, the weight adjustment algorithm is as follows:

[0089] Assume the initial weight vector is w0=(w1,w2,…,w n ), where n is the number of evaluation indicators; collect new psychological data X new =(x1, x2,…, x m ), where x i is the psychological reaction data vector of the person being tested during the assessment, and m is the number of psychological reaction data; according to the performance of the person being tested during the assessment, the score of each indicator is calculated as s = (s1, s2, ..., s n), calculate the product of the score and the initial weight, and get the preliminary evaluation result S i =s·w0, where the score of the indicator is calculated by the following steps:

[0090] Preprocess the psychological reaction data of the tested flight attendants, extract features related to the evaluation indicators from the preprocessed data, convert the extracted feature information into quantifiable scores or indicator values, establish a corresponding scoring model based on the evaluation indicators and feature information, and establish the scoring model based on a large amount of data verification and expert review to ensure its validity and reliability. Input the psychological reaction data of the tested flight attendants into the scoring model to obtain the score s of each evaluation indicator;

[0091] According to the comparison between the preliminary evaluation results and the actual performance of the simulation task, the weights are adjusted and the performance adjustment function f is introduced. p (s,w0,α), this function adjusts the weight according to the score s, the initial weight w0 and the performance adjustment coefficient α, and the adjusted weight is w p , w p =f p (s,w0,α), Where α is the performance adjustment factor, is the average score, σ s is the standard deviation of the score, and the performance adjustment coefficient α can be set according to the overall performance level of the flight attendants in the simulated task to reflect the relative strength of their psychological competence. 0,i It represents the initial weight of the i-th evaluation indicator, s i is the score of the ith indicator, w p,i It represents the weight of the i-th evaluation indicator after performance adjustment;

[0092] According to the historical evaluation data H=(h1,h2,…,h k ), where h j Represents the data of the jth historical evaluation, and calculates the historical trend of each indicator t=(t1, t2, …, t n ), introduce the trend adjustment function f t (t,w p ,β), the adjusted weight w t =f t (t,w p ,β),w t,i =w p,i ·(1+β·t i ), where β is the trend adjustment coefficient, which can be set according to the stability and reliability of historical data, w t,i It represents the weight of the i-th evaluation indicator after trend adjustment, t i is the historical trend of the ith indicator;

[0093] Normalize the adjusted weights to ensure that the sum of the weights is 1. The normalized weight vector w f =(w 1,f ,w 2,f ,…,w n,f ), calculated by the following formula: Among them, w i,f is the final adjusted weight of the i-th indicator, n is the number of evaluation indicators, and the output is the adjusted weight vector w f .

[0094] Through the above algorithm, the weights are dynamically adjusted to more accurately reflect the performance level of flight attendants on various evaluation indicators, thereby improving the accuracy of the evaluation results. It can identify which indicators the flight attendants perform well on and which indicators need improvement, thereby providing flight attendants with personalized training and development suggestions.

[0095] In one embodiment of the present invention, the comprehensive evaluation report generation module includes:

[0096] A data integration unit, used to receive and integrate data from the psychological data collection module, the physiological index data collection module and the dynamic weight generation module;

[0097] The comparison and verification unit is used to compare and verify the psychological load assessment results output by the psychological load assessment module with the psychological competency assessment results output by the psychological competency assessment module to ensure the consistency and correlation between the two. The comparison and verification unit can use statistical analysis methods, such as correlation analysis, regression analysis, etc., to evaluate the degree of correlation between the two assessment results;

[0098] The comprehensive evaluation unit, based on the comparison and verification results and the dynamic weights provided by the dynamic weight generation module, performs weighted summation on each evaluation index to obtain the comprehensive psychological competence score of the tested flight attendant;

[0099] The report generation unit generates a comprehensive psychological competency assessment report including scores, strengths, weaknesses and personalized suggestions based on the comprehensive assessment results. The report is output in the form of an electronic document or a paper document for review and use by the tested flight attendants, airline management and training personnel.

[0100] In one embodiment of the present invention, the comprehensive evaluation report generation module also includes a feedback mechanism for collecting and organizing feedback on the evaluation report from the flight attendants being evaluated, airline management, and trainers. The feedback can be used to improve and optimize the design and implementation methods of the evaluation system, thereby improving the accuracy and practicality of the evaluation results.

[0101] By introducing biofeedback technology and a dynamic weight adjustment mechanism, the above-mentioned system can more objectively evaluate the psychological competence level of flight attendants and reduce the influence of subjective factors. The system provides scientific evaluation tools and methods for airlines, which helps airlines to more accurately select, train and evaluate flight attendants, improve the overall service quality and management level. By dynamically adjusting the weight of each evaluation indicator based on the real-time performance of flight attendants and historical evaluation data, it can more accurately predict the future performance of flight attendants, and can more flexibly adapt to the individual differences of different flight attendants, ensuring that the evaluation results can truly reflect the actual psychological competence level of each person being tested.

[0102] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the psychological competence of civil aviation crew members by integrating biofeedback, characterized in that: The following steps are involved: a) Set up assessment indicators for the psychological competence of civil aviation flight attendants, which are determined based on psychological principles and the professional characteristics of flight attendants; b) Collect the psychological data of the flight attendants being tested during the assessment and pre-process the collected psychological data; c) Based on machine learning algorithms, the pre-processed psychological data is trained to generate dynamic weights for each evaluation indicator; d) While the flight attendants are performing the psychological assessment task, the physiological index data of the flight attendants are collected synchronously using biofeedback technology; e) Fuse psychological data with physiological index data, extract key features using deep learning algorithms, build a psychological load assessment model, and evaluate the changes in psychological load of the tested person in the simulation task in real time; f) Compare and verify the psychological load assessment results with the psychological competency assessment results, and combine them with dynamic weights to generate a comprehensive psychological competency assessment report for the flight attendants.

2. The method for evaluating the psychological competence of civil aviation crew members integrating biofeedback according to claim 1 is characterized in that: The psychological data acquisition method in step b) includes one or more of questionnaire survey results, interview records and results output by psychological testing software.

3. The method for evaluating the psychological competence of civil aviation crew members integrating biofeedback according to claim 1 is characterized in that: The physiological indicator data in step d) includes at least one of heart rate, blood pressure and skin conductance.

4. The method for evaluating the psychological competence of civil aviation crew members integrating biofeedback according to claim 1 is characterized in that: The weight adjustment in step c) is based on one or more of the performance of the person being assessed, historical assessment data, and industry standards.

5. The method for evaluating the psychological competence of civil aviation crew members integrating biofeedback according to claim 1 is characterized in that: The deep learning algorithm in step e) includes a convolutional neural network or a recurrent neural network, which is used to fuse the psychological data with the physiological indicator data, extract key features, and build a psychological load assessment model.

6. A civil aviation crew psychological competency assessment system integrating biofeedback, characterized in that: The method for evaluating the psychological competence of civil aviation crew members integrating biofeedback as described in any one of claims 1 to 5 above comprises: an evaluation index setting module, a psychological data collection module, a dynamic weight generation module, a physiological index data collection module, a psychological load assessment model construction module and a comprehensive evaluation report generation module; The evaluation index setting module is used to set the evaluation index of civil aviation flight attendants' psychological competence. The evaluation index is determined based on the principles of psychology and the professional characteristics of flight attendants. The psychological data collection module is used to collect the psychological reaction data of the flight attendants being tested during the assessment; The dynamic weight generation module trains the preprocessed psychological data based on the machine learning algorithm to generate the dynamic weights of each evaluation indicator; The physiological index data collection module is used to collect the physiological index data of the flight attendants while the flight attendants are performing the psychological assessment task; The psychological load assessment model building module is used to integrate psychological data with physiological index data, build a psychological load assessment model, and evaluate the changes in the psychological load of the tested person in the simulation task in real time; The comprehensive assessment report generation module is used to compare and verify the psychological load assessment results with the psychological competence assessment results, and generate a comprehensive psychological competence assessment report for the tested flight attendants in combination with dynamic weights.

7. The civil aviation crew psychological competency assessment system integrating biofeedback according to claim 6, characterized in that: The model building module uses at least one of the weighted average method, the hierarchical analysis method or the fuzzy comprehensive evaluation method to normalize and standardize the psychological data to build a psychological competency assessment model.

8. The civil aviation crew psychological competency assessment system integrating biofeedback according to claim 6, characterized in that: The physiological data acquisition module includes at least one of a heart rate monitoring submodule, a blood pressure monitoring submodule and a skin conductance monitoring submodule, wherein the heart rate monitoring submodule is used to collect the heart rate of the measured flight attendant, the blood pressure monitoring submodule is used to collect the blood pressure of the measured flight attendant, and the skin conductance monitoring submodule is used to collect the skin conductance data of the measured flight attendant.

9. The civil aviation crew psychological competency assessment system integrating biofeedback according to claim 6, characterized in that: The dynamic weight generation module also includes a weight adjustment algorithm. The weight adjustment algorithm dynamically adjusts the weight of each evaluation indicator according to the real-time performance of the person being tested in the simulation task and the historical evaluation data. The weight adjustment algorithm is as follows: Assume the initial weight vector is w0=(w1,w2,…,w n ), where n is the number of evaluation indicators; collect new psychological data X new =(x1, x2,…, x m ), where x i is the psychological reaction data vector of the person being tested during the assessment, and m is the number of psychological reaction data; according to the performance of the person being tested during the assessment, the score of each indicator is calculated as s = (s1, s2, ..., s n ), calculate the product of the score and the initial weight, and get the preliminary evaluation result S i =s·w0; According to the comparison between the preliminary evaluation results and the actual performance of the simulation task, the weights are adjusted and the performance adjustment function f is introduced. p (s,w0,α), the adjusted weight is w p , w p =f p (s,w0,α), Where α is the performance adjustment factor, is the average score, σ s is the standard deviation of the scores; According to the historical evaluation data H=(h1,h2,…,h k ), where h j Represents the data of the jth historical evaluation, and calculates the historical trend of each indicator t=(t1, t2, …, t n ), introduce the trend adjustment function f t (t,w p ,β), the adjusted weight w t =f t (t,w p ,β),w t,i =w p,i ·(1+β·t i ), where β is the trend adjustment coefficient; Normalize the adjusted weights to ensure that the sum of the weights is 1. The normalized weight vector w f =(w 1,f ,w 2,f ,…,w n,f ), calculated by the following formula: Output the adjusted weight vector w f .

10. The civil aviation crew psychological competency assessment system integrating biofeedback according to claim 6, characterized in that: The comprehensive evaluation report generation module includes: A data integration unit, used to receive and integrate data from the psychological data collection module, the physiological index data collection module and the dynamic weight generation module; The comparison and verification unit is used to compare and verify the psychological load assessment results output by the psychological load assessment module with the psychological competency assessment results output by the psychological competency assessment module to ensure the consistency and relevance between the two. The comprehensive evaluation unit, based on the comparison and verification results and the dynamic weights provided by the dynamic weight generation module, performs weighted summation on each evaluation index to obtain the comprehensive psychological competence score of the tested flight attendant; The report generation unit generates a comprehensive psychological competency assessment report containing scores, strengths, weaknesses and personalized suggestions based on the comprehensive assessment results. The report is output in the form of electronic or paper documents for review and use by the tested flight attendants, airline management and training personnel.

Images