Psychological crisis intervention system after flight accident

Abstract

The invention provides a psychological crisis intervention system after a flight accident, and relates to the technical field of psychological crisis intervention. The data acquisition module is used for acquiring a psychological data set of a to-be-tested crowd, the first evaluation module is used for determining a target crowd according to the psychological data set, the storage module is used for storing a psychological intervention method, and the first intervention module is used for generating a corresponding intervention scheme for the target crowd according to the psychological intervention method. The second evaluation module is used for setting a time threshold value and evaluating the target crowd which passes through the time threshold value and accepts intervention again to obtain an evaluation result of each target person in the target crowd, and the second intervention module is used for performing intervention effect judgment according to the evaluation result of each target person to obtain a judgment result. The problem that accurate and timely psychological crisis intervention is difficult to realize when the psychological crisis intervention after the flight accident is handled in the prior art is solved.

Description

Technical Field

[0001] The invention relates to the technical field of psychological crisis intervention, in particular to a psychological crisis intervention system after a flight accident. Background Art

[0002] For psychological crisis intervention after flight accidents, the traditional manual reinforcement model is to expand the psychological counseling team to be stationed at the airport and conduct manual carpet operations after the accident. However, the cost is high, and the daily expenses of maintaining a large team are staggering; the efficiency is low, and interviews and manual analysis are time-consuming, making it difficult to quickly cover all employees; standardization is difficult, and different styles of personnel lead to different intervention quality, and it is impossible to deal with complex crises; improve general software, add case libraries, etc. to adapt to aviation. However, the underlying architecture is not optimized for the flight industry, the analysis is superficial, the scale lacks key dimensions, the intervention resources are universal and not exclusive, it is difficult to meet the needs of different positions, and the rehabilitation effect is poor; multiple institutions piece together a collaborative model and temporarily convene forces from all parties. Communication is difficult, responsibilities are chaotic, data is not connected, the team lacks running-in, and response is slow;

[0003] In summary, the various existing technical means for psychological crisis intervention after flight accidents are either not timely and have limited coverage, or are not targeted and have scattered functions. They cannot provide a complete, efficient, and one-stop solution that fits the special situations and personnel characteristics of the aviation industry, making it difficult to achieve accurate and timely psychological crisis intervention. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a psychological crisis intervention system after a flight accident. The present invention solves the problem in the prior art that it is difficult to achieve accurate and timely psychological crisis intervention when dealing with psychological crisis intervention after a flight accident.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A post-flight accident psychological crisis intervention system, comprising:

[0007] A data acquisition module, a first evaluation module, a storage module, a first intervention module, a second evaluation module, and a second intervention module connected in sequence;

[0008] The second intervention module is connected to the storage module;

[0009] The data acquisition module is used to acquire the psychological data set of the population to be tested. The first evaluation module is used to determine the target population according to the psychological data set. The storage module is used to store psychological intervention methods, where the information intervention methods include: personal methods and team methods. The first intervention module is used to generate corresponding intervention plans for the target population according to the psychological intervention methods. The second evaluation module is used to set a time threshold and re-evaluate the target population that has passed the time threshold and has received intervention to obtain the evaluation results of each target person in the target population. The second intervention module is used to judge the intervention effect according to the evaluation results of each target person to obtain a judgment result, and the judgment result includes: excellent intervention, stop intervention; good intervention, continue to intervene with the current intervention plan; ineffective intervention, regenerate the corresponding intervention plan according to the personal method.

[0010] Preferably, the data acquisition module includes:

[0011] a sensor sub-module, a questionnaire survey sub-module, and a data integration sub-module;

[0012] The sensor sub-module is used to acquire the physiological index data of the population to be tested. The questionnaire survey sub-module is used to set up a psychological questionnaire to acquire the psychological state data set of the population to be tested. The data integration sub-module is used to preprocess the psychological state data set and the physiological index data, obtain the preprocessed data set, and perform data matching and merging according to the user ID and time stamp in the current data set to obtain the corresponding psychological data set.

[0013] Preferably, the first evaluation module includes:

[0014] a characterization value calculation sub-module and a comparison sub-module

[0015] The characterization value calculation sub-module is used to calculate the emotion characterization value, the work and rest characterization value, and the exercise characterization value, and obtain the mental health characterization value according to the emotion characterization value, the work and rest characterization value, and the exercise characterization value. The comparison sub-module is used to set a characterization threshold and compare it with the mental health characterization value to obtain a comparison result. If the comparison result is large, it is determined as abnormal.

[0016] Preferably, the calculation formula of the mental health characterization value is:

[0017]

[0018] where XL is the mental health characterization value, Q is the emotion characterization value, Z is the work and rest characterization value, S is the exercise characterization value, C is the social characterization value, A is the cognitive characterization value, and α, β, γ, δ, ∈ are the first preset weight factor, the second preset weight factor, the third preset weight factor, the fourth preset weight factor, and the fifth preset weight factor, respectively.

[0019] Preferably, the first intervention module includes:

[0020] A target setting sub-module, an effect prediction sub-module, and a solution generation sub-module;

[0021] The target setting sub-module is used to set an intervention target according to the target population and the corresponding mental health characterization value. The effect prediction sub-module is used to calculate an effect score according to the intervention target, the personal method, and the team method to obtain an evaluation score set. The solution generation sub-module is used to generate a corresponding intervention solution according to the evaluation score.

[0022] Preferably, the target setting sub-module includes:

[0023] A data acquisition unit, a feature extraction unit, a preset target construction unit, a scoring unit, and a target determination unit;

[0024] The data acquisition unit is used to receive the mental health characterization value. The feature extraction unit is used to extract the key features of the mental health characterization value to obtain feature data. The preset target construction unit is used to construct a target prediction model and generate a preset target according to the feature data. The scoring unit is used to perform multi-dimensional scoring on the preset target to obtain a scoring set. The target determination unit is used to adjust the preset target according to the scoring set to obtain the final target.

[0025] Preferably, the scoring unit includes:

[0026] A scoring dimension determination sub-unit, a scoring data acquisition sub-unit, a scoring calculation sub-unit, and a scoring display sub-unit;

[0027] The scoring dimension determination sub-unit is used to determine multi-dimensional scoring indicators, which include: adaptability scoring, expected effect scoring, feasibility scoring, feedback scoring, and time sensitivity scoring. The scoring data acquisition sub-unit is used for multi-angle scoring criteria, which include: expert scoring, historical data analysis scoring, and user feedback requirements. The scoring calculation sub-unit is used to set corresponding weights for the multi-dimensional scoring indicators according to the multi-angle scoring criteria. The scoring calculation sub-unit is used to calculate the scores of the multi-dimensional scoring indicators according to the set weights. The scoring display sub-unit is used to display the scores of the respective dimension indicators in a legend.

[0028] Preferably, the effect prediction sub-module includes:

[0029] An effect prediction model construction unit and an evaluation score calculation unit;

[0030] The effect prediction model construction unit is used to construct an effect prediction model according to a neural network. The evaluation score calculation unit obtains the key feature vectors of the final target and inputs them into the effect prediction model to generate an evaluation score set.

[0031] Preferably, the effect prediction model construction unit includes:

[0032] a parameter acquisition subunit and a model training subunit;

[0033] The parameter acquisition subunit is used to obtain the key parameter set of the intervention method. The model construction subunit uses the intervention effect as the dependent variable, uses the key parameter set and the key feature vectors of the target as independent variables, and trains based on a neural network model to construct an effect prediction model.

[0034] Preferably, the expression of the effect prediction model is:

[0035] E t = f(W·h(X t ,E t-1 ) + b) + A·F(R t );

[0036] where, E t is the predicted result of the effect score at the current time step, X t is the input feature vector at the current time step, E t-1 is the predicted effect score at the previous time step, W is the feature weight matrix, representing the learning effect of features and feedback information, h(X t ,E t-1 ) is the feature extraction network, which processes the combination of the current feature and the previous prediction output to capture more complex relationships, b is the bias term, A is the weight coefficient, adjusting the influence degree of the feedback information on the current prediction, R t is the user feedback signal, and F(R t ) is the feedback adjustment function, which is responsible for converting the user feedback into model input to affect future predictions.

[0037] The present invention discloses the following technical effects:

[0038] The present invention provides a psychological crisis intervention system after a flight accident, including: a data acquisition module, a first evaluation module, a storage module, a first intervention module, a second evaluation module, and a second intervention module that are connected in sequence; the second intervention module is connected to the storage module; the data acquisition module is used to collect a psychological data set of a population to be tested, the first evaluation module is used to determine a target population according to the psychological data set, the storage module is used to store psychological intervention methods, wherein the information intervention methods include: individual methods and team methods, the first intervention module is used to generate a corresponding intervention plan for the target population according to the psychological intervention methods, the second evaluation module is used to set a time threshold and re-evaluate the target population that has undergone the time threshold and has received intervention to obtain the evaluation results of each target person in the target population, the second intervention module is used to judge the intervention effect according to the evaluation results of each target person to obtain a judgment result, and the judgment result includes: excellent intervention, stop intervention; good intervention, continue to intervene with the current intervention plan; ineffective intervention, regenerate a corresponding intervention plan according to the individual method. By means of the sequentially connected data acquisition module, the present invention comprehensively uses sensors and questionnaires to be able to collect the psychological and physiological data of the population to be tested in an all-round way. Such a diverse data source helps to form a more accurate psychological state assessment and reduce the information deviation caused by individual differences; the connected first intervention module generates a personalized intervention plan according to the evaluation results to ensure that the intervention measures can better meet the specific needs of the target population. Such an ability to respond in a timely manner can effectively relieve the urgent needs of an individual when experiencing a psychological crisis, thereby reducing the risk of deterioration of the psychological crisis; the second evaluation module is introduced to re-evaluate by setting a time threshold to be able to monitor the persistence and suitability of the intervention effect. Such a dynamic management mechanism can not only adjust the intervention plan in a timely manner, but also ensure that the intervention measures are not implemented excessively or insufficiently, improving the effectiveness of the intervention; the second intervention module makes an intervention effect judgment according to the evaluation results of each target population, providing a scientific basis for the subsequent intervention plan. Such a feedback mechanism promotes the personalization and optimization of the intervention, and through continuous iterative improvement, helps to achieve a more lasting intervention effect. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0040] Figure 1 It is a schematic structural diagram of a psychological crisis intervention system after a flight accident provided by an embodiment of the present invention.

[0041] Description of the reference numerals in the drawings:

[0042] 1 - Data acquisition module, 2 - First evaluation module, 3 - Storage module, 4 - First intervention module, 5 - Second evaluation module, 6 - Second intervention module. Detailed implementation manners

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0044] To make the above - mentioned objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0045] As Figure 1 shown, the present invention provides a psychological crisis intervention system after a flight accident, including:

[0046] A data acquisition module 1, a first evaluation module 2, a storage module 3, a first intervention module 4, a second evaluation module 5, and a second intervention module 6 that are connected in sequence;

[0047] The second intervention module 6 is connected to the storage module 3;

[0048] The data acquisition module 1 is used to collect the psychological data set of the population to be tested, the first evaluation module 2 is used to determine the target population according to the psychological data set, the storage module 3 is used to store psychological intervention methods, where the information intervention methods include: individual methods and team methods. The first intervention module 4 is used to generate a corresponding intervention plan for the target population according to the psychological intervention methods. The second evaluation module 5 is used to set a time threshold and re - evaluate the target population that has passed the time threshold and has received intervention to obtain the evaluation results of each target person in the target population. The second intervention module 6 is used to judge the intervention effect according to the evaluation results of each target person to obtain a judgment result. The judgment result includes: excellent intervention, stop intervention; good intervention, continue intervention with the current intervention plan; ineffective intervention, regenerate a corresponding intervention plan according to the individual method.

[0049] Specifically, the determination of the intervention effect:

[0050] Case 1 (excellent intervention): After the intervention of individual A, the mental health characterization value rises, and it is determined that the intervention result is excellent, so the intervention is stopped.

[0051] Case 2 (Good Intervention): Individual B had only a slight improvement (remaining at 65 points). Continue with the current intervention plan and increase the frequency of group support meetings.

[0052] Case 3 (Ineffective Intervention): If Individual C (with a mental health representation value of 60 points) shows no obvious change after intervention, then regenerate their intervention plan according to personal methods and switch to intensive intervention of cognitive behavioral therapy.

[0053] Furthermore, the data collection module 1 includes:

[0054] A sensor sub-module, a questionnaire survey sub-module, and a data integration sub-module;

[0055] The sensor sub-module is used to collect physiological index data of the population to be measured. The questionnaire survey sub-module is used to set up a psychological questionnaire to collect the psychological state data set of the population to be measured. The data integration sub-module is used to preprocess the psychological state data set and the physiological index data, obtain the preprocessed data set, and perform data matching and merging according to the user ID and timestamp in the current data set to obtain the corresponding psychological data set.

[0056] Specifically, the sensor sub-module: Real-time collects the physiological index data of the population to be measured, and uses wearable devices (such as Fitbit bracelets or smart watches) to monitor the physiological parameters of individuals. Specific parameters include: Heart rate: The number of heartbeats per minute. Respiratory rate: The number of breaths per minute. Sleep monitoring: Monitor sleep duration and sleep quality. Data collection: The device uploads the physiological data to the cloud server every 5 minutes, recording the timestamp and user ID.

[0057] The questionnaire survey sub-module: Collects the psychological state data of the population to be measured through a psychological questionnaire. Questionnaire design: Design a standardized psychological state questionnaire, including the following dimensions: Depression scale (such as PHQ-9 scale): Evaluate the severity of depressive symptoms. Anxiety scale (such as GAD-7 scale): Evaluate the severity of anxiety symptoms. Life satisfaction scale: Evaluate the individual's subjective satisfaction with the current living situation.

[0058] Data collection: Send the questionnaire link through an online platform, and the population to be measured needs to fill in the questionnaire before each assessment. The data will include the timestamp and user ID.

[0059] Furthermore, the first evaluation module 2 includes:

[0060] A representation value calculation sub-module and a comparison sub-module;

[0061] The characterization value calculation sub-module is used to calculate the emotion characterization value, the work and rest characterization value, and the exercise characterization value, and obtain the mental health characterization value based on the emotion characterization value, the work and rest characterization value, and the exercise characterization value. The comparison sub-module is used to set a characterization threshold and compare it with the mental health characterization value to obtain a comparison result. If the comparison result is greater, it is determined as abnormal.

[0062] Specifically, the calculation of the work and rest characterization value: The average sleep duration and sleep quality data (such as deep sleep and light sleep durations) of the user are obtained through the sensor sub-module. According to the average sleep duration of the user per week, a threshold (such as 6 hours) is set to obtain the work and rest characterization value. The calculation of the exercise characterization value: The daily step count and activity level data recorded by the smart watch are used. A daily step count target (such as 8000 steps) is set. If the user's step count is 6000 steps, then the exercise characterization value is: Exercise characterization value = 8000 steps - 6000 steps = 2000 steps, not reaching the target.

[0063] Furthermore, the calculation formula for the mental health characterization value is:

[0064]

[0065] Wherein, XL is the mental health characterization value, Q is the emotion characterization value, Z is the work and rest characterization value, S is the exercise characterization value, C is the social interaction characterization value, A is the cognitive characterization value, and α, β, γ, δ, ∈ are the first preset weight factor, the second preset weight factor, the third preset weight factor, the fourth preset weight factor, and the fifth preset weight factor respectively.

[0066] Specifically, the mental health characterization value in this embodiment integrates multiple mental health dimensions (emotion, work and rest, exercise, social interaction, and cognition), enabling a comprehensive assessment of an individual's mental health status, rather than being limited to a single indicator.

[0067] Furthermore, the first intervention module 4 includes:

[0068] A goal setting sub-module, an effect prediction sub-module, and a plan generation sub-module;

[0069] The goal setting sub-module is used to set an intervention goal according to the target population and the corresponding mental health characterization value. The effect prediction sub-module is used to calculate the effect score based on the intervention goal, the personal method, and the team method to obtain an evaluation score set. The plan generation sub-module is used to generate a corresponding intervention plan according to the evaluation score.

[0070] Specifically, the goal setting sub-module: Sets a specific intervention goal according to the mental health characterization value of the target population. Receives the mental health characterization value (XL) of the target population from the evaluation module. For example, the mental health characterization value of a certain user is 60 points.

[0071] Classify the target:

[0072] Emotion management: Adjust the anxiety score to less than 7.

[0073] Improve work and rest: The goal is to have no less than 7 hours of effective sleep per day.

[0074] Increase exercise: Set the daily step goal to 8000 steps.

[0075] Example of goal setting:

[0076] For users with a mental health representation value of 60 points, set the following intervention goals:

[0077] Emotion score is improved from 4 to 2

[0078] Work and rest score is improved from 4 to 6

[0079] Exercise score is improved from 3 to 5

[0080] Social score is improved from 2 to 4

[0081] Calculate the effectiveness score according to the intervention goals and methods:

[0082] Individual methods: Such as individual psychological counseling (CBT).

[0083] Team methods: Such as group psychological support.

[0084] Calculation of effectiveness score:

[0085] Input the intervention goals and selected methods into the model to calculate the effectiveness scores of each plan. For example:

[0086] The expected effectiveness score of individual psychological counseling is 85 points.

[0087] The expected effectiveness score of group psychological support is 75 points.

[0088] Example of evaluation score set:

[0089] Assume the current evaluation results for users are:

[0090] Case 1 (individual psychological counseling): Effectiveness score = 85

[0091] Case 2 (group psychological support): Effectiveness score = 75

[0092] Generate specific intervention plans based on the evaluation scores:

[0093] Plan selection criteria: Prioritize and select the plan with a higher effectiveness score according to the effectiveness score.

[0094] Solution Generation: Based on the evaluation score set, generate a personalized intervention plan for the user, such as:

[0095] Individual Psychological Counseling: Aimed at emotion management and sleep schedule improvement.

[0096] Group Psychological Support: Participate in group support group activities every week for a preset period of time to enhance social skills and emotional support.

[0097] Specific Plan Example:

[0098] For a user with a mental health representation value of 60, the generated effective intervention plan is:

[0099] Intervention Plan: Select individual psychological counseling as the main intervention method.

[0100] Conduct 1-hour individual counseling per week. During a period of intervention, gradually improve emotional coping strategies. Arrange a comprehensive mental health assessment every two weeks to track the progress of the intervention and adjust the intervention method in a timely manner.

[0101] Furthermore, the target setting sub-module includes:

[0102] A data acquisition unit, a feature extraction unit, a preset target construction unit, a scoring unit, and a target determination unit;

[0103] The data acquisition unit is used to receive the mental health representation value. The feature extraction unit is used to extract the key features of the mental health representation value to obtain feature data. The preset target construction unit is used to construct a target prediction model and generate a preset target according to the feature data. The scoring unit is used to perform multi-dimensional scoring on the preset target to obtain a scoring set. The target determination unit is used to adjust the preset target according to the scoring set to obtain the final target.

[0104] Furthermore, the scoring unit includes:

[0105] A scoring dimension determination sub-unit, a scoring data acquisition sub-unit, a scoring calculation sub-unit, and a scoring display sub-unit;

[0106] The scoring dimension determination subunit is used to determine multi-dimensional scoring indicators, and the multi-dimensional scoring indicators include: adaptability score, expected effect score, feasibility score, feedback score and time sensitivity score. The scoring data acquisition subunit is used for multi-angle scoring standards, and the multi-angle scoring standards include: expert score, historical data analysis score and user feedback requirements. The scoring calculation subunit is used to set corresponding weights for the multi-dimensional scoring indicators according to the multi-angle scoring standards. The scoring calculation subunit is used to calculate the scores of the multi-dimensional scoring indicators according to the set weights. The scoring display subunit is used to display the scores of the various dimensional indicators in a legend.

[0107] Specifically, adaptability score: measures an individual's ability to adapt to new environments or situations.

[0108] Expected effect rating: Evaluate whether the expected effect of the plan is reasonable.

[0109] Feasibility score: Analyzes the technical and resource availability of the implementation plan.

[0110] Feedback Rating: Evaluate the suitability of a solution based on feedback from users or experts.

[0111] Time sensitivity score: assesses whether the intervention is effective within the intended time.

[0112] Specifically, personalized weight adjustment: for different user groups (such as the elderly, women, and young people with high work pressure), evaluate the characteristics of each group and adjust the weight to reflect the sensitivity of different groups to each scoring dimension. For example, for groups with high pressure, the weight of "feedback score" and "time sensitivity score" can be increased to promote timely intervention.

[0113] Furthermore, the effect prediction submodule includes:

[0114] Effect prediction model building unit and evaluation score calculation unit;

[0115] The effect prediction model construction unit is used to construct an effect prediction model according to a neural network, and the evaluation score calculation unit obtains the key feature vector of the final target and inputs it into the effect prediction model to generate an evaluation score set.

[0116] Specifically, for feature extraction, the following are the instructions: Extract key features, such as: User features: age, gender, occupation. Psychological state features: emotional representation values, work and rest representation values, exercise representation values, etc. Intervention method features: selected method, expected intervention goals and their duration.

[0117] By maximizing the accuracy and reducing errors, the cross-validation method is used to continuously adjust the model parameters, such as the learning rate, batch size, regularization coefficient, etc., to achieve the best prediction effect. After the model training is completed, the test set is used for evaluation to obtain the prediction accuracy (such as AUC, F1 score, etc.).

[0118] Further, the effect prediction model construction unit includes:

[0119] A parameter acquisition subunit and a model training subunit;

[0120] The parameter acquisition subunit is used to obtain the key parameter set of the intervention method; the model construction subunit is used to take the intervention effect as the dependent variable, take the key parameter set and the key feature vector of the target as the independent variables, and train based on the neural network model to construct an effect prediction model.

[0121] Specifically, the expression of the effect prediction model is:

[0122] E t = f(W·h(X t ,E t-1 ) + b) + A·F(R t );

[0123] Where, E t is the predicted result of the effect score at the current time step, X t is the input feature vector at the current time step, E t-1 is the predicted result of the effect score at the previous time step, W is the feature weight matrix, representing the learning effect of the features and feedback information, h(X t ,E t-1 ) is the feature extraction network, which processes the combination of the current feature and the previous prediction output to capture more complex relationships, b is the bias term, A is the weight coefficient, adjusting the influence degree of the feedback information on the current prediction, R t is the user feedback signal, F(R t ) is the feedback adjustment function, which is responsible for converting the user feedback into the model input, so as to affect future predictions.

[0124] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same and similar parts among the embodiments can be referred to each other.

[0125] In this article, specific examples are used to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A post-flight accident psychological crisis intervention system, characterized in that: include: A data acquisition module, a first evaluation module, a storage module, a first intervention module, a second evaluation module, and a second intervention module connected in sequence; The second intervention module is connected to the storage module; The data acquisition module is used to collect psychological data sets of the population to be tested, the first evaluation module is used to determine the target population based on the psychological data sets, and the storage module is used to store psychological intervention methods, wherein the information intervention methods include: personal methods and team methods, the first intervention module is used to generate corresponding intervention plans for the target population according to the psychological intervention methods, the second evaluation module is used to set a time threshold, and re-evaluate the target population after the time threshold and after receiving the intervention to obtain the evaluation results of each target person in the target population, the second intervention module is used to judge the intervention effect according to the evaluation results of each target person to obtain a judgment result, and the judgment result includes: excellent intervention, stop intervention; good intervention, continue intervention using the current intervention plan; intervention is ineffective, and regenerate the corresponding intervention plan according to the personal method.

2. A post-flight accident psychological crisis intervention system according to claim 1, characterized in that: The data acquisition module comprises: sensor submodule, questionnaire submodule and data integration submodule; The sensor submodule is used to collect physiological indicator data of the population to be tested, the questionnaire survey submodule is used to set a psychological questionnaire to collect a psychological state data set of the population to be tested, and the data integration submodule is used to preprocess the physiological indicator data of the psychological state data set to obtain a preprocessed data set and perform data matching and merging according to the user ID and timestamp in the current data set to obtain a corresponding psychological data set.

3. The post-flight accident psychological crisis intervention system according to claim 1, characterized in that: The first evaluation module includes: Characterization value calculation submodule and comparison submodule The characterization value calculation submodule is used to calculate the emotion characterization value, the work and rest characterization value and the exercise characterization value and obtain the mental health characterization value based on the emotion characterization value, the work and rest characterization value and the exercise characterization value. The comparison submodule is used to set the characterization threshold and compare the size with the mental health characterization value to obtain a comparison result. If the comparison result is large, it is judged as abnormal.

4. A post-flight accident psychological crisis intervention system according to claim 3, characterized in that: The calculation formula of the mental health characterization value is: Among them, XL is the mental health representation value, Q is the emotion representation value, Z is the work and rest representation value, S is the exercise representation value, C is the social representation value, A is the cognitive representation value, α, β, γ, δ, ∈ are the first preset weight factor, the second preset weight factor, the third preset weight factor, the fourth preset weight factor and the fifth preset weight factor respectively.

5. The post-flight accident psychological crisis intervention system according to claim 3, characterized in that: The first intervention module includes: Goal setting submodule, effect prediction submodule and solution generation submodule; The goal setting submodule is used to set intervention goals based on the target population and the corresponding mental health characterization values. The effect prediction submodule is used to calculate the effect score based on the intervention goals and the personal method and team method to obtain an evaluation score set. The plan generation submodule is used to generate a corresponding intervention plan based on the evaluation score.

6. A post-flight accident psychological crisis intervention system according to claim 5, characterized in that: The target setting submodule includes: Data acquisition unit, feature extraction unit, preset target construction unit, scoring unit and target determination unit; The data acquisition unit is used to accept the mental health characterization value, the feature extraction unit is used to extract the key features of the mental health characterization value to obtain feature data, the preset target construction unit is used to construct a target prediction model and generate a preset target based on the feature data, the scoring unit is used to perform multi-dimensional scoring on the preset target to obtain a scoring set, and the target determination unit is used to adjust the preset target based on the scoring set to obtain a final target.

7. A post-flight accident psychological crisis intervention system according to claim 6, characterized in that: The scoring unit comprises: Rating dimension determination subunit, rating data acquisition subunit, rating calculation subunit and rating display subunit; The scoring dimension determination subunit is used to determine multi-dimensional scoring indicators, and the multi-dimensional scoring indicators include: adaptability score, expected effect score, feasibility score, feedback score and time sensitivity score. The scoring data acquisition subunit is used for multi-angle scoring standards, and the multi-angle scoring standards include: expert score, historical data analysis score and user feedback requirements. The scoring calculation subunit is used to set corresponding weights for the multi-dimensional scoring indicators according to the multi-angle scoring standards. The scoring calculation subunit is used to calculate the scores of the multi-dimensional scoring indicators according to the set weights. The scoring display subunit is used to display the scores of the various dimensional indicators in a legend.

8. The post-flight accident psychological crisis intervention system according to claim 7, characterized in that: The effect prediction submodule includes: Effect prediction model building unit and evaluation score calculation unit; The effect prediction model construction unit is used to construct an effect prediction model according to a neural network, and the evaluation score calculation unit obtains the key feature vector of the final target and inputs it into the effect prediction model to generate an evaluation score set.

9. A post-flight accident psychological crisis intervention system according to claim 8, characterized in that: The effect prediction model building unit comprises: Parameter acquisition subunit and model training subunit; The parameter acquisition subunit is used to acquire the key parameter set of the intervention method; the model construction subunit is used to take the intervention effect as the dependent variable, take the key parameter set and the key feature vector of the target as the independent variable and train based on the neural network model to construct an effect prediction model.

10. A post-flight accident psychological crisis intervention system according to claim 9, characterized in that: The expression of the effect prediction model is: E t =f(W·h(X t ,E t-1 )+b)+A·F(R t ); Among them, E t The prediction result of the effect score at the current time step, X t is the input feature vector E of the current time step t-1 is the effect score prediction of the previous time step, W is the feature weight matrix, which represents the learning effect of the features and feedback information, h(X t ,E t-1 ) is a feature extraction network that processes the combination of the current feature and the previous prediction output to capture more complex relationships. b is a bias term, A is a weight coefficient that adjusts the impact of feedback information on the current prediction, and R t is the user feedback signal, F(R t ) is the feedback adjustment function, which is responsible for converting user feedback into model input, thereby affecting future predictions.

Images