Training monitoring system for pilot

Abstract

The invention discloses a training monitoring system for a pilot, and the system comprises a flight training collection subsystem which is used for carrying out the collection of flight training related information in the flight training process of the pilot; the daily training acquisition subsystem is used for acquiring daily training related information in the daily training process of the pilot; the data processing module is used for processing the flight training related information and the daily training related information to generate flight training prompt information and daily training prompt information; and the information sending module is used for sending the flight training prompt information and the daily training prompt information to a preset receiving terminal. According to the invention, more comprehensive pilot training can be carried out, and the abnormity of the pilot can be found and prompted in time in the training process.

Description

Technical Field

[0001] The present invention relates to the field of monitoring systems, and in particular to a training monitoring system for pilots. Background Art

[0002] Flight accident statistics show that human error is one of the main causes of accidents. Pilot fatigue, inattention, and psychological stress can seriously impact flight safety. Therefore, real-time monitoring of pilot status and the prompt detection and correction of abnormal behavior are crucial to improving flight safety.

[0003] Therefore, during the pilot training process, a detection system is needed to monitor the pilot, even if any abnormality is found in the pilot.

[0004] The existing training monitoring system has a single monitoring type, which makes it impossible to detect abnormal pilot status in time, which has a certain impact on the use of the training monitoring system. Therefore, a training monitoring system for pilots is proposed. Summary of the Invention

[0005] The technical problem to be solved by the present invention is how to solve the problem that the existing training monitoring system has a single monitoring type and cannot detect the abnormal status of the pilot in time, and provides a training monitoring system for pilots.

[0006] The present invention solves the above-mentioned technical problems through the following technical solutions, which include: The flight training collection subsystem is used to collect flight training related information during the pilot's flight training; Daily training collection subsystem is used to collect information related to daily training during the pilots' daily training; A data processing module is used to process flight training related information and daily training related information to generate flight training prompt information and daily training prompt information; The information sending module is used to send flight training prompt information and daily training prompt information to a preset receiving terminal.

[0007] Furthermore, the specific process of the flight training collection subsystem collecting flight training related information during the pilot's flight training is as follows: The flight training acquisition subsystem includes simulated flight image acquisition, voice acquisition module and eye movement acquisition module; The simulated flight image acquisition module is used to collect the pilot's facial image information during flight training; The voice acquisition module is used to collect pilots' voice information during training; The eye movement acquisition module is used to collect the pilot's eye movement information during training.

[0008] Furthermore, the process of obtaining the flight training prompt information is as follows: Extracting the pilot's facial image information, processing the pilot's facial image information, and obtaining a first parameter; extracting the pilot's voice information and processing the pilot's voice information to obtain a second parameter; Processing the pilot's eye movement information to obtain a third parameter; When any one of the first parameter, the second parameter or the third parameter is abnormal, a flight training prompt message is generated.

[0009] Furthermore, the process of obtaining the first parameter is as follows: Extract the pilot's facial image information and locate the eye image information from the facial image information; Extract feature points from the eye image information and mark the two corners of the left eye as points e1 and e2; Connect points e1 and e2 to obtain line segment L1. Continue to collect eye image information. When the eyes are closed, capture point M1 where the upper eyelid first touches line segment L1. Draw a perpendicular line R1 with point M1 as the reference point. Mark the intersection of perpendicular line R1 and the lower eyelid as M2. Connect M1 and M2 to obtain the evaluation line F1; Mark the two corners of the right eye as points p1 and p2; Connect points p1 and p2 to obtain line segment L2. When the eyes are closed, collect the intersection point W1 of the upper eyelid and the first point where the upper eyelid touches L2. Draw a perpendicular line R2 with point W1 as the reference point, and mark the intersection point of the perpendicular line R2 and the lower eyelid as W2. Connect W1 and W2 to obtain the evaluation line F2; Continuously collect the length Gi of the evaluation line F1 and the length Ui of the evaluation line F2, where i is the number of collections; Then extract the number T1 of Gi that is less than the preset value and the number T2 of Ui that is less than the preset value; The first parameter is obtained through the formula (T1+T2)*α / 2i=Tt, where α is the correction value, 0.95≤α≤0.99, and α is proportional to T1+T2; When the first parameter is greater than the preset value, it indicates that there is an abnormality in the first parameter.

[0010] Furthermore, the process of obtaining the second parameter is as follows: Extract the pilot's voice information, process the pilot's voice information, and obtain abnormal pronunciation, speaking speed information, voice clarity and voice emotion information; The process for determining abnormal pronunciation is as follows: extract the real-time pronunciation of each character in the pilot's voice information, compare the real-time pronunciation of each character with the standard pronunciation, and mark the character as abnormal if the similarity between the real-time pronunciation and the standard pronunciation is less than a preset value; The process of acquiring voice emotion information is as follows: emotional analysis is performed on the pilot's voice information to extract the number of occurrences of anger and anxiety in the voice information, thus acquiring the voice emotion information; The number of abnormal pronunciations is extracted, and then the pilot's voice information is processed to obtain the total number of pronunciation characters; Calculate the ratio of the number of abnormal pronunciations to the total number of pronounced characters to obtain the abnormal pronunciation ratio; The second parameter consists of abnormal pronunciation ratio, speech speed information, speech clarity and speech emotion information; When any one of the following occurs: the proportion of abnormal pronunciation is greater than the preset value, the speech speed information exceeds the preset range, the speech clarity is less than the preset value, and the speech emotion information is greater than the preset value, it indicates that the second parameter is abnormal.

[0011] Furthermore, the process of obtaining the third parameter is as follows: Extracting the pilot's eye movement information, which is the pilot's gaze point position; Continuously monitor the pilot's gaze position for a preset period of time and record the length of time the pilot's gaze position remains within a preset area, including the instrument panel and operating area; Calculate the ratio of the time the pilot's gaze point stays in the preset area to the preset time, and obtain the percentage of stay in the preset area; At the same time, during the continuous monitoring of the pilot's gaze position, the number of times the pilot's gaze position stays at a single point for more than the warning threshold is also recorded, that is, the number of abnormal stays; The percentage of stays in the preset area and the number of abnormal stays constitute the third parameter; When the percentage of stays in the preset area is less than the preset value or the number of abnormal stays is greater than the preset value, it indicates that the third parameter is abnormal.

[0012] Furthermore, the specific process of the daily training collection subsystem collecting daily training related information during the pilot's daily training is as follows: The daily training acquisition subsystem includes a daily training image acquisition module and a pilot psychological testing module; The daily training image acquisition module is used to collect daily training images of pilots; The pilot psychological test module is used to randomly select a time to conduct psychological tests on pilots and obtain the pilots' psychological test scores.

[0013] Furthermore, the process of obtaining the daily training prompt information is as follows: Extracting the pilots' daily training images, which are real-time images of the pilots performing pull-up training; Feature points were extracted from the pilots' daily training images, and the left shoulder joint was marked as A1, and the right shoulder joint was marked as B1. Mark the left elbow joint point as point A2, and the right elbow joint point as point B2; Mark the left wrist joint point as point A3, and the right wrist joint point as point B3; Connect points A1, A2, and A3 to form the left arm line R1; Connect points B1, B2, and B3 to form the right arm line R2; Detect the left arm line R1 and detect the difference between the maximum angle and the minimum angle of the left arm line R1, that is, the left angle difference; Detect the right arm line R1 and the difference between the maximum angle and the minimum angle of the right arm line R2, that is, the right angle difference; Continuously collect the left angle difference and the right angle difference in unit time, extract the number of times the left angle difference is less than a preset value Y1 and the number of times the right angle difference is less than a preset value Y2, and mark the preset time length as H; The number of abnormalities is obtained through the formula (Y1+Y2) / H=Yy. When the number of abnormalities is greater than the preset value, a daily training reminder message is generated; The psychological test scores are extracted, and when the psychological test scores are less than the preset value for two consecutive times, daily training reminder information is generated.

[0014] Compared with the existing technology, the present invention has the following advantages: the training monitoring system for pilots can improve the quality of flight training. By collecting various information such as facial images, voice, eye movements, etc. during flight training and performing detailed analysis and processing, it can accurately evaluate the pilot's performance in training, such as whether there are problems such as fatigue, lack of concentration, and irregular operation, thereby providing pilots with more targeted improvement suggestions to help them improve their flying skills and operational levels. Based on the long-term accumulation and in-depth analysis of pilot training data, weak links and problems in the training process can be discovered, and then the flight training plan can be optimized, and the training content and intensity can be reasonably arranged to make the training more scientific and efficient, thereby improving the overall training quality of pilots.

[0015] The system can monitor the pilot's status during flight training in real time. Once an abnormal situation is detected, such as pilot fatigue or operational errors, it can immediately generate flight training reminder information and send it to the preset receiving terminal, reminding the pilot or instructor to take timely measures to avoid safety accidents caused by fatigue or improper operation, effectively improving the safety of flight training.

[0016] Through comprehensive analysis of pilots' daily training and flight training data, potential risks that pilots may face, such as excessive psychological stress and bad operating habits, can be discovered in advance, allowing for early intervention and correction, thus preventing flight safety issues from occurring at the source. Improve training management efficiency; The pilot psychological testing module in the daily training collection subsystem can randomly select time to conduct psychological tests on pilots and obtain scores. This helps to understand the pilots' psychological quality and promptly detect their psychological stress, anxiety and other problems, so as to carry out targeted psychological counseling and training, help pilots develop good psychological quality, and better cope with various complex situations during flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0018] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process. However, the protection scope of the present invention is not limited to the following embodiment.

[0019] like Figure 1 As shown, this embodiment provides a technical solution: a training monitoring system for pilots, comprising: The flight training collection subsystem is used to collect flight training related information during the pilot's flight training; Daily training collection subsystem is used to collect information related to daily training during the pilots' daily training; A data processing module is used to process flight training related information and daily training related information to generate flight training prompt information and daily training prompt information; The information sending module is used to send flight training prompt information and daily training prompt information to a preset receiving terminal.

[0020] The specific process of the flight training collection subsystem collecting flight training related information during the pilot's flight training is as follows: The flight training acquisition subsystem includes simulated flight image acquisition, voice acquisition module and eye movement acquisition module; The simulated flight image acquisition module is used to collect the pilot's facial image information during flight training; The voice acquisition module is used to collect pilots' voice information during training; The eye movement acquisition module is used to collect the pilot's eye movement information during training; By simulating flight image acquisition, voice acquisition, and eye movement acquisition, the system comprehensively collects pilot training information from multiple dimensions, including vision, hearing, and eye movement. This multi-dimensional information fusion can more comprehensively reflect the pilot's state during flight training, including body posture, mental state, and concentration, thereby providing richer and more accurate data support for pilot training evaluation.

[0021] It's difficult to fully assess a pilot's ability and state based solely on a single dimension of information. For example, voice alone may not accurately determine whether a pilot is paying attention. However, combining eye movement information with facial image information can more accurately determine whether they are focused on the operation. This comprehensive assessment method helps to more comprehensively assess a pilot's flying ability and psychological state, providing a more reliable basis for subsequent training guidance. This improves training safety and effectiveness; The flight training data acquisition subsystem collects and analyzes real-time data on pilots' facial images, voice, and eye movements. If an abnormality is detected, such as pilot fatigue, distraction, or operational error, the system immediately issues a warning signal, prompting the pilot or instructor to take timely action to avoid safety incidents caused by fatigue or improper operation, thereby effectively improving flight training safety.

[0022] By analyzing collected flight training data, we can gain a deeper understanding of pilots' training problems and shortcomings. For example, if we find that a pilot's eye movements in certain operational steps don't meet specifications, or that they frequently hesitate or make errors in their voice commands, we can adjust the training content and methods accordingly, strengthen training in these weak areas, and improve the effectiveness and relevance of the training.

[0023] Different pilots may exhibit different performance and needs during flight training. The flight training data acquisition subsystem collects and analyzes information such as facial expressions, voice intonation, and eye movement patterns to accurately identify each pilot's individual characteristics and training needs. For example, some pilots may become easily nervous when faced with complex flight missions. The voice acquisition module can detect nervousness in their voices and provide targeted psychological counseling and training support.

[0024] Based on the multi-dimensional information collected, a personalized training plan can be developed for each pilot. For example, for pilots with poor eye control, relevant eye movement training content can be added to help improve their attention allocation and visual search abilities. For pilots with unclear voice commands, voice training can be strengthened to improve their communication skills with ground control and crew members.

[0025] The process of obtaining the flight training prompt information is as follows: Extracting the pilot's facial image information, processing the pilot's facial image information, and obtaining a first parameter; extracting the pilot's voice information and processing the pilot's voice information to obtain a second parameter; Processing the pilot's eye movement information to obtain a third parameter; When any one of the first parameter, the second parameter or the third parameter is abnormal, a flight training prompt message is generated.

[0026] The process of obtaining the first parameter is as follows: Extract the pilot's facial image information and locate the eye image information from the facial image information; Extract feature points from the eye image information and mark the two corners of the left eye as points e1 and e2; Connect points e1 and e2 to obtain line segment L1. Continue to collect eye image information. When the eyes are closed, capture point M1 where the upper eyelid first touches line segment L1. Draw a perpendicular line R1 with point M1 as the reference point. Mark the intersection of perpendicular line R1 and the lower eyelid as M2. Connect M1 and M2 to obtain the evaluation line F1; Mark the two corners of the right eye as points p1 and p2; Connect points p1 and p2 to obtain line segment L2. When the eyes are closed, collect the intersection point W1 of the upper eyelid and the first point where the upper eyelid touches L2. Draw a perpendicular line R2 with point W1 as the reference point, and mark the intersection point of the perpendicular line R2 and the lower eyelid as W2. Connect W1 and W2 to obtain the evaluation line F2; Continuously collect the length Gi of the evaluation line F1 and the length Ui of the evaluation line F2, where i is the number of collections; Then extract the number T1 of Gi that is less than the preset value and the number T2 of Ui that is less than the preset value; The first parameter is obtained through the formula (T1+T2)*α / 2i=Tt, where α is the correction value, 0.95≤α≤0.99, and α is proportional to T1+T2; When the first parameter is greater than the preset value, it means that there is an abnormality in the first parameter; By extracting eye image information and calculating the length changes of the evaluation lines F1 and F2, the pilot's blinking behavior can be quantified into specific data (such as the length of Gi and Ui). The setting of the quantification method makes the monitoring of blinking behavior more accurate, avoids the errors of subjective judgment, and provides a reliable data basis for subsequent analysis and evaluation.

[0027] Continuously collect eye image information and calculate the evaluation line length in real time, which can monitor the changes in pilot blinking behavior in real time; This dynamic monitoring method can promptly capture abnormal changes in blink frequency, such as a sudden increase in the number of blinks, thus providing the possibility of timely detection of potential problems. It can effectively judge fatigue and attention status. Frequent blinking is often one of the external manifestations of pilot fatigue or lack of concentration. By calculating the first parameter, Tt, and comparing it with a preset value, it is possible to objectively determine whether the pilot is experiencing abnormal conditions such as fatigue or inattention. Compared to traditional subjective assessment methods, this method is more scientific and objective, and can more accurately reflect the pilot's actual condition.

[0028] Early warning of fatigue risk: When the first parameter Tt exceeds the preset value, it indicates that the pilot may be fatigued or in other abnormal conditions. The system can immediately issue a warning signal to remind the pilot or instructor to take timely measures, such as suspending training, taking a rest, etc. At the same time, the length change speed of Gi and Ui can also be collected and calculated. The length change speed of Gi and Ui in the normal eye blinking state is the reference value. If the collected length change speed of Gi and Ui is greater than or less than the reference value, it may be that the body has overreacted to the stimulation, or it may be that the spirit is relatively depressed and in a state of distress.

[0029] The early warning mechanism can effectively prevent flight accidents caused by fatigue or inattention, and improve the safety of flight training; Based on the monitoring results of the first parameter, the instructor can make personalized training adjustments tailored to the pilot's specific condition. For example, for a fatigued pilot, appropriate rest arrangements or adjustment of training intensity can be made; for a pilot experiencing difficulty concentrating, additional attention training can be provided. This personalized training adjustment helps improve training effectiveness while preventing physical and mental fatigue caused by overtraining or improper training.

[0030] Long-term monitoring and analysis of the first parameter can reveal patterns in pilot fatigue and attention span during different training phases. Coaches can use these patterns to optimize training plans, rationally arranging training time and intensity, and avoiding cumulative pilot fatigue caused by inappropriate training arrangements, thereby improving the overall effectiveness and safety of training. During pilot simulation training, frequent blinking may lead to the following adverse effects: Frequent blinking can cause pilots to lose visual information multiple times in a short period of time, especially in some critical operation phases such as takeoff, landing, and flight in complex weather conditions. They may miss important visual clues such as instrument readings, flight attitude indicators, runway markings, etc., thereby affecting the accuracy and safety of flight operations.

[0031] Blinking itself is a brief visual interruption. Frequent blinking can distract pilots, making it difficult for them to maintain a high level of concentration on the flight mission. This can lead to an incomplete perception of the flight environment, delayed response to emergencies, and increased risk of accidents.

[0032] Frequent blinking can cause visual disturbances and distractions, preventing pilots from fully understanding and mastering key training points and operational skills, significantly reducing training effectiveness. For example, during flight attitude adjustment training, pilots cannot accurately observe changes in the aircraft's attitude, making it difficult to achieve the desired training objectives.

[0033] Increase the difficulty and time cost of training. In order to compensate for the poor training effect caused by frequent blinking, it may be necessary to increase the number and time of training, which not only increases the training burden of pilots, but also increases the training cost.

[0034] Physical and psychological impact on pilots: Increased eye fatigue: Normally, blinking is to keep the eyes moist and clean. However, excessive blinking can actually increase eye fatigue, leading to dryness, soreness, pain, and other discomfort, affecting pilots' visual health.

[0035] Frequent blinking may make the pilot aware of his or her poor condition, thus causing psychological pressure such as anxiety and tension. This psychological pressure will further affect the pilot's flight performance, forming a vicious circle. Impact on flight safety Reduced situational awareness: Situational awareness refers to the pilot's ability to perceive, understand and predict the flight environment. Frequent blinking may cause the pilot's perception of the flight environment to be discontinuous, making it difficult to accurately understand the surrounding situation, thereby reducing the level of situational awareness. For example, when flying in complex airspace, it is impossible to detect the approach of other aircraft or the potential risk of air conflict in a timely manner; Due to factors such as incomplete visual information acquisition, lack of concentration, and psychological stress, the possibility of pilots making human errors in simulation training increases significantly. If these errors occur in actual flight, they may lead to serious flight accidents.

[0036] The process of obtaining the second parameter is as follows: Extract the pilot's voice information, process the pilot's voice information, and obtain abnormal pronunciation, speaking speed information, voice clarity and voice emotion information; The process for determining abnormal pronunciation is as follows: extract the real-time pronunciation of each character in the pilot's voice information, compare the real-time pronunciation of each character with the standard pronunciation, and mark the character as abnormal if the similarity between the real-time pronunciation and the standard pronunciation is less than a preset value; The process of acquiring voice emotion information is as follows: emotional analysis is performed on the pilot's voice information to extract the number of occurrences of anger and anxiety in the voice information, thus acquiring the voice emotion information; The number of abnormal pronunciations is extracted, and then the pilot's voice information is processed to obtain the total number of pronunciation characters; Calculate the ratio of the number of abnormal pronunciations to the total number of pronounced characters to obtain the abnormal pronunciation ratio; The second parameter consists of abnormal pronunciation ratio, speech speed information, speech clarity and speech emotion information; When any of the following occurs: the proportion of abnormal pronunciation is greater than the preset value, the speech speed information exceeds the preset range, the speech clarity is less than the preset value, and the speech emotion information is greater than the preset value, it indicates that the second parameter is abnormal; By analyzing multiple dimensions, including abnormal pronunciation, speech rate, voice clarity, and voice emotion, the system can comprehensively reflect a pilot's state during flight training. This multi-dimensional analysis can more accurately identify whether a pilot is experiencing fatigue, tension, anxiety, or other issues, providing a more comprehensive assessment basis for flight training.

[0037] A single dimension of speech information may not fully reflect a pilot's condition. By comprehensively analyzing multiple dimensions, a more accurate assessment of a pilot's overall performance can be made. For example, rapid speech may indicate nervousness, while abnormal pronunciation may indicate fatigue or a lack of concentration. Combining this information allows for a more comprehensive assessment of a pilot's condition.

[0038] By continuously analyzing the pilot's voice information, the system can monitor changes in the pilot's status in real time. If it detects abnormal pronunciation, abnormal speaking speed, unclear speech, or abnormal emotions, the system can immediately issue a warning signal, prompting the pilot or instructor to take timely measures to avoid operational errors caused by fatigue or stress, thereby improving flight training safety.

[0039] Voice emotion analysis can detect negative emotions such as anger and anxiety in pilots, which can affect their decision-making and operational performance. By promptly identifying and addressing these emotional issues, we can prevent flight accidents caused by emotional fluctuations and improve flight training safety.

[0040] Based on the monitoring results of the second parameter, the instructor can make personalized training adjustments to address the pilot's specific issues. For example, if a pilot is found to have abnormal pronunciation, voice training can be strengthened; if emotional abnormalities are detected, psychological counseling can be provided. This personalized training adjustment helps improve training effectiveness and help pilots better master flying skills.

[0041] Long-term monitoring and analysis of voice information can reveal performance trends at different stages of pilot training. Instructors can use these trends to optimize training plans, rationalizing training content and intensity, and avoiding pilot fatigue or slow skill improvement caused by poor training arrangements.

[0042] The analysis of emotional information in voice can indirectly reflect the pilot's psychological state. By monitoring the frequency of emotions such as anger and anxiety, coaches can promptly identify pilots' psychological stress points and provide targeted psychological counseling and support to help pilots develop good psychological qualities. During flight training, pilots may face various pressures and challenges, and emotional management is crucial. Voice emotion analysis can provide pilots with real-time emotional feedback, helping them learn to better manage their emotions during flight, stay calm and focused, and thus improve their ability to cope with complex situations.

[0043] The process of obtaining the third parameter is as follows: Extracting the pilot's eye movement information, which is the pilot's gaze point position; Continuously monitor the pilot's gaze position for a preset period of time and record the length of time the pilot's gaze position remains within a preset area, including the instrument panel and operating area; Calculate the ratio of the time the pilot's gaze point stays in the preset area to the preset time, and obtain the percentage of stay in the preset area; At the same time, during the continuous monitoring of the pilot's gaze position, the number of times the pilot's gaze position stays at a single point for more than the warning threshold is also recorded, that is, the number of abnormal stays; The percentage of stays in the preset area and the number of abnormal stays constitute the third parameter; When the percentage of stays in the preset area is less than the preset value or the number of abnormal stays is greater than the preset value, it means that the third parameter is abnormal; By recording the length of time a pilot's gaze remains within pre-set areas (such as the instrument panel and operating area) and calculating the ratio of this amount to the pre-set duration (the percentage of time spent in pre-set areas), the pilot's attention allocation in key areas can be quantified. This quantitative method can intuitively reflect whether the pilot is focusing sufficient time and attention on important flight tasks.

[0044] The system also records the number of times a pilot's gaze remains on a single point for longer than the warning threshold (abnormal gaze). This helps identify whether the pilot is excessively focused on a specific point and ignoring other important information. This abnormal gaze behavior may indicate that the pilot is having difficulty with certain operations or is overly focused, requiring further attention and adjustment.

[0045] Continuously monitoring the pilot's eye movements during flight training can detect anomalies in attention allocation in real time. If a third parameter becomes abnormal (the percentage of dwells in a preset area or the number of abnormal dwells exceeds a preset value), the system immediately issues a warning signal, prompting the pilot or instructor to adjust attention allocation promptly. This prevents operational errors caused by inattention or improper allocation, thereby improving flight training safety.

[0046] Long-term monitoring and analysis of pilots' eye movements can reveal potential attention allocation issues, such as a tendency to become distracted or overly focused during specific tasks or phases. Instructors can use this information to proactively intervene and adjust training, preventing accidents caused by attention issues and improving the overall safety of flight training.

[0047] The specific process of the daily training collection subsystem collecting daily training related information during the pilot's daily training is as follows: The daily training acquisition subsystem includes a daily training image acquisition module and a pilot psychological testing module; The daily training image acquisition module is used to collect daily training images of pilots; The pilot psychological test module is used to randomly select a time to conduct psychological tests on pilots and obtain the pilots' psychological test scores.

[0048] The process of obtaining daily training reminder information is as follows: Extracting the pilots' daily training images, which are real-time images of the pilots performing pull-up training; Feature points were extracted from the pilots' daily training images, and the left shoulder joint was marked as A1, and the right shoulder joint was marked as B1. Mark the left elbow joint point as point A2, and the right elbow joint point as point B2; Mark the left wrist joint point as point A3, and the right wrist joint point as point B3; Connect points A1, A2, and A3 to form the left arm line R1; Connect points B1, B2, and B3 to form the right arm line R2; Detect the left arm line R1 and detect the difference between the maximum angle and the minimum angle of the left arm line R1, that is, the left angle difference; Detect the right arm line R1 and the difference between the maximum angle and the minimum angle of the right arm line R2, that is, the right angle difference; Continuously collect the left angle difference and the right angle difference in unit time, extract the number of times the left angle difference is less than a preset value Y1 and the number of times the right angle difference is less than a preset value Y2, and mark the preset time length as H; The number of abnormalities is obtained through the formula (Y1+Y2) / H=Yy. When the number of abnormalities is greater than the preset value, a daily training reminder message is generated; Extract the psychological test scores. When the psychological test scores are less than the preset value for two consecutive times, a daily training reminder message is generated. The daily training acquisition subsystem not only collects footage of pilots' daily training but also uses a psychological testing module to obtain psychological status scores. This multi-dimensional information fusion enables a more comprehensive assessment of a pilot's training status, encompassing both the standardization of their physical movements and the stability of their psychological qualities, providing richer data support for comprehensive pilot assessments.

[0049] By analyzing imaging data and psychological test scores, a comprehensive assessment of a pilot's performance in daily training can be made. For example, even if a pilot performs well in physical movements but scores poorly on psychological tests, this could indicate potential psychological issues that require further attention and intervention.

[0050] Improve training effectiveness and quality, standardize body movements, and accurately monitor the standardization of pilots' movements during exercises like pull-ups by extracting feature points and analyzing angle differences in daily training images. For example, by detecting the difference between the maximum and minimum angles of the arm line, it can determine whether the pilot's movements are standard, allowing for timely detection and correction of irregular movements, thereby improving training effectiveness.

[0051] Based on daily training prompts, coaches can adjust training plans accordingly. For example, if a pilot is found to have irregular movements during pull-up training, relevant training content can be added; if a pilot scores low on a psychological test, psychological counseling can be arranged or the training intensity can be adjusted, thereby optimizing the training plan and improving training quality. The psychological testing module can randomly select time to conduct psychological tests on pilots, promptly detecting changes in their mental state. For example, if the psychological test scores are lower than the preset value for two consecutive times, it may indicate that the pilot is experiencing psychological stress or emotional problems, requiring timely intervention.

[0052] By analyzing psychological test scores, instructors can provide pilots with targeted psychological counseling. For example, for anxious pilots, relaxation training or psychological counseling can be arranged to help them relieve stress and improve their mental health.

[0053] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0054] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0055] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A training monitoring system for pilots, characterized in that: include: The flight training collection subsystem is used to collect flight training related information during the pilot's flight training; Daily training collection subsystem is used to collect information related to daily training during the pilots' daily training; A data processing module is used to process flight training related information and daily training related information to generate flight training prompt information and daily training prompt information; The information sending module is used to send flight training prompt information and daily training prompt information to a preset receiving terminal.

2. A pilot training monitoring system according to claim 1, characterized in that: The specific process of the flight training collection subsystem collecting flight training related information during the pilot's flight training is as follows: The flight training acquisition subsystem includes simulated flight image acquisition, voice acquisition module and eye movement acquisition module; The simulated flight image acquisition module is used to collect the pilot's facial image information during flight training; The voice acquisition module is used to collect pilots' voice information during training; The eye movement acquisition module is used to collect the pilot's eye movement information during training.

3. A pilot training monitoring system according to claim 2, characterized in that: The process of obtaining the flight training prompt information is as follows: Extracting the pilot's facial image information, processing the pilot's facial image information, and obtaining a first parameter; extracting the pilot's voice information and processing the pilot's voice information to obtain a second parameter; Processing the pilot's eye movement information to obtain a third parameter; When any one of the first parameter, the second parameter or the third parameter is abnormal, a flight training prompt message is generated.

4. A pilot training monitoring system according to claim 3, characterized in that: The process of obtaining the first parameter is as follows: Extract the pilot's facial image information and locate the eye image information from the facial image information; Extract feature points from the eye image information and mark the two corners of the left eye as points e1 and e2; Connect points e1 and e2 to obtain line segment L1. Continue to collect eye image information. When the eyes are closed, capture point M1 where the upper eyelid first touches line segment L1. Draw a perpendicular line R1 with point M1 as the reference point. Mark the intersection of perpendicular line R1 and the lower eyelid as M2. Connect M1 and M2 to obtain the evaluation line F1; Mark the two corners of the right eye as points p1 and p2; Connect points p1 and p2 to obtain line segment L2. When the eyes are closed, collect the intersection point W1 of the upper eyelid and the first point where the upper eyelid touches L2. Draw a perpendicular line R2 with point W1 as the reference point, and mark the intersection point of the perpendicular line R2 and the lower eyelid as W2. Connect W1 and W2 to obtain the evaluation line F2; Continuously collect the length Gi of the evaluation line F1 and the length Ui of the evaluation line F2, where i is the number of collections; Then extract the number T1 of Gi that is less than the preset value and the number T2 of Ui that is less than the preset value; The first parameter is obtained through the formula (T1+T2)*α / 2i=Tt, where α is the correction value, 0.95≤α≤0.99, and α is proportional to T1+T2; When the first parameter is greater than the preset value, it indicates that there is an abnormality in the first parameter.

5. A pilot training monitoring system according to claim 3, characterized in that: The process of obtaining the second parameter is as follows: Extract the pilot's voice information, process the pilot's voice information, and obtain abnormal pronunciation, speaking speed information, voice clarity and voice emotion information; The process for determining abnormal pronunciation is as follows: extract the real-time pronunciation of each character in the pilot's voice information, compare the real-time pronunciation of each character with the standard pronunciation, and mark the character as abnormal if the similarity between the real-time pronunciation and the standard pronunciation is less than a preset value; The process of acquiring voice emotion information is as follows: emotional analysis is performed on the pilot's voice information to extract the number of occurrences of anger and anxiety in the voice information, thus acquiring the voice emotion information; The number of abnormal pronunciations is extracted, and then the pilot's voice information is processed to obtain the total number of pronunciation characters; Calculate the ratio of the number of abnormal pronunciations to the total number of pronounced characters to obtain the abnormal pronunciation ratio; The second parameter consists of abnormal pronunciation ratio, speech speed information, speech clarity and speech emotion information; When any one of the following occurs: the proportion of abnormal pronunciation is greater than the preset value, the speech speed information exceeds the preset range, the speech clarity is less than the preset value, and the speech emotion information is greater than the preset value, it indicates that the second parameter is abnormal.

6. A pilot training monitoring system according to claim 3, characterized in that: The process of obtaining the third parameter is as follows: Extracting the pilot's eye movement information, which is the pilot's gaze point position; Continuously monitor the pilot's gaze position for a preset period of time and record the length of time the pilot's gaze position remains within a preset area, including the instrument panel and operating area; Calculate the ratio of the time the pilot's gaze point stays in the preset area to the preset time, and obtain the percentage of stay in the preset area; At the same time, while continuously monitoring the pilot's gaze position, the number of times the pilot's gaze position stays at a single point for more than the warning threshold is also recorded, that is, the number of abnormal stays; The percentage of stays in the preset area and the number of abnormal stays constitute the third parameter; When the percentage of stays in the preset area is less than the preset value or the number of abnormal stays is greater than the preset value, it indicates that the third parameter is abnormal.

7. A pilot training monitoring system according to claim 1, characterized in that: The specific process of the daily training collection subsystem collecting daily training related information during the pilot's daily training is as follows: The daily training acquisition subsystem includes a daily training image acquisition module and a pilot psychological testing module; The daily training image acquisition module is used to collect daily training images of pilots; The pilot psychological test module is used to randomly select a time to conduct psychological tests on pilots and obtain the pilots' psychological test scores.

8. The pilot training monitoring system according to claim 1, characterized in that: The process of obtaining the daily training prompt information is as follows: Extracting the pilots' daily training images, which are real-time images of the pilots performing pull-up training; Feature points were extracted from the pilots' daily training images, and the left shoulder joint was marked as A1, and the right shoulder joint was marked as B1. Mark the left elbow joint point as point A2, and the right elbow joint point as point B2; Mark the left wrist joint point as point A3, and the right wrist joint point as point B3; Connect points A1, A2, and A3 to form the left arm line R1; Connect points B1, B2, and B3 to form the right arm line R2; Detect the left arm line R1 and detect the difference between the maximum angle and the minimum angle of the left arm line R1, that is, the left angle difference; Detect the right arm line R1 and the difference between the maximum angle and the minimum angle of the right arm line R2, that is, the right angle difference; Continuously collect the left angle difference and the right angle difference in unit time, extract the number of times the left angle difference is less than a preset value Y1 and the number of times the right angle difference is less than a preset value Y2, and mark the preset time length as H; The number of abnormalities is obtained through the formula (Y1+Y2) / H=Yy. When the number of abnormalities is greater than the preset value, a daily training reminder message is generated; The psychological test scores are extracted, and when the psychological test scores are less than the preset value for two consecutive times, daily training reminder information is generated.

Images