Pilot training evaluation method, device and equipment and storage medium

Abstract

The invention discloses a pilot training evaluation method, device and equipment and a storage medium, and belongs to the technical field of aviation, and the method comprises the steps: inputting the training data of a to-be-evaluated pilot into a pilot training evaluation model, and generating a training evaluation result of the to-be-evaluated pilot based on an output result; a training mode of the pilot training evaluation model comprises the following steps: performing action recognition on an obtained human body motion image of a pilot in a training process to obtain a first action data set; performing motion posture analysis on the obtained human motion video of the pilot in the training process to construct a second motion data set; marking the first action data set and the second action data set based on the flight action standard parameters to obtain a training sample set; and training the constructed pilot training evaluation model according to the training sample set, thereby obtaining an accurate pilot training evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of aviation technology, and in particular to a pilot training evaluation method, device, equipment and storage medium. Background Art

[0002] With the development of aviation technology, cockpits have become highly automated and intelligent. According to surveys released by Boeing and Airbus, the total number of accidents caused by aircraft performance has been declining over the past 60 years. The latest statistical survey shows that human factors account for 75% of flight accidents, of which crew errors account for the majority. Therefore, the training of aircraft pilots is particularly important.

[0003] The traditional pilot training evaluation method is a subjective evaluation made by the instructor's previous experience, which will be affected by personal experience, knowledge level and judgment criteria, resulting in deviations in the pilot training evaluation results and making it difficult to accurately reflect the pilot's competence quality. Summary of the invention

[0004] The present invention provides a pilot training evaluation method, device, equipment and storage medium. By accurately processing sample data, an accurate pilot training evaluation model is trained, thereby obtaining accurate pilot training evaluation results, thereby promoting the intelligent process of aviation training.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a pilot training evaluation method, comprising:

[0006] Inputting the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generating a training evaluation result of the pilot to be evaluated based on the output result;

[0007] The training method of the pilot training evaluation model includes:

[0008] Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images;

[0009] Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture;

[0010] Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set;

[0011] The constructed pilot training evaluation model is trained according to the training sample set.

[0012] As one preferred solution, before inputting the training data of the pilot to be evaluated into the trained pilot training evaluation model, the method further includes:

[0013] Acquiring the identity information of the pilot to be evaluated, wherein the identity information includes at least face information, iris information, certificate information and fingerprint information;

[0014] Perform a security check on the identity information.

[0015] As one preferred solution, the setting of the standard parameters of the flight action includes:

[0016] Semantic recognition of ICAO regulations, CAAC regulations, civil aviation flight manuals and training program requirements;

[0017] Based on the semantic recognition results, a standardized database is constructed;

[0018] The standard parameters of flight actions corresponding to each training scenario are extracted from the standardized database.

[0019] As one preferred solution, the output result at least includes flight time, flight distance, accident rate and time for handling special situations;

[0020] The generating the training evaluation result of the pilot to be evaluated based on the output result includes:

[0021] The flight time, the flight distance, the accident rate and the time for handling special situations are input into a pre-constructed pilot competency index evaluation relationship to obtain a competency evaluation result of the pilot to be evaluated, wherein the pilot competency index evaluation relationship is:

[0022] Z I =F T +F D +A I +A C

[0023] Among them, Z I is the pilot competency assessment result, P is the weight coefficient of flight time, Q is the weight coefficient of flight distance, R is the weight coefficient of accident rate, S is the weight coefficient of pilot handling time, F T is the flight time, F D is the flight distance, A I is the event rate, A C Time for handling special situations;

[0024] The training evaluation result of the pilot to be evaluated is generated based on the competency evaluation result.

[0025] As one preferred solution, after generating the training evaluation result of the pilot to be evaluated based on the output result, the method further includes:

[0026] Generate a matching flight training optimization suggestion log according to the competency assessment result of the pilot to be assessed, wherein the flight training optimization suggestion log at least includes a competency-specific training plan and a training scenario adjustment plan;

[0027] The flight training optimization suggestion log is sent to the mobile terminal of the pilot to be evaluated, the cloud server, and the training data middle station respectively.

[0028] As one preferred solution, after generating the training evaluation result of the pilot to be evaluated based on the output result, the method further includes:

[0029] The training data of the pilot to be evaluated is uploaded to a matching database for storage, wherein the storage process is designed to store the authority instruction bound to the training data of the pilot to be evaluated.

[0030] Another embodiment of the present invention provides a pilot training evaluation device, comprising:

[0031] An evaluation module, used for inputting the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generating a training evaluation result of the pilot to be evaluated based on an output result;

[0032] The training method of the pilot training evaluation model includes:

[0033] Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images;

[0034] Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture;

[0035] Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set;

[0036] The constructed pilot training evaluation model is trained according to the training sample set.

[0037] Another embodiment of the present invention provides a pilot training evaluation device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the pilot training evaluation method described above when executing the computer program.

[0038] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when a device where the computer-readable storage medium is located executes the computer program, the pilot training evaluation method as described above is implemented.

[0039] Yet another embodiment of the present invention provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium and is suitable for being read and executed by a processor, so that a computer device having the processor executes the pilot training evaluation method as described above.

[0040] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0041] (1) The present invention can analyze the data of the pilot training process. By sequentially processing the image data and the video data in a targeted manner, more accurate action features can be obtained, thereby providing accurate data support for the construction of subsequent sample data, and further obtaining a more accurate pilot training evaluation model, thereby avoiding evaluation bias caused by the instructor's subjective experience and promoting the intelligent process of pilot training evaluation.

[0042] (2) By constructing a pilot competency index evaluation relationship, the pilot training results can be quantitatively expressed, thereby providing quantitative support for subsequent recommendations and guidance. For example, targeted training courses can be designed based on the pilot competency evaluation results, and corresponding special flight scenarios can be constructed based on the courses. The flight safety risk behaviors such as pilot fatigue and slow reaction in specific scenarios can be studied, and the correlation between pilot physiological parameters and flight safety can be analyzed, thereby improving the quality of flight training and flight safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a pilot training evaluation method in one embodiment of the present invention;

[0044] Figure 2 is a structural block diagram of a pilot training evaluation device in one embodiment of the present invention;

[0045] Figure 3 It is a structural block diagram of a pilot training evaluation device in one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0048] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0049] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0050] An embodiment of the present invention provides a pilot training evaluation method. For details, see Figure 1 , Figure 1 The flowchart of the pilot training evaluation method in one embodiment of the present invention is shown, which specifically includes step S101:

[0051] S101, inputting the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generating a training evaluation result of the pilot to be evaluated based on an output result;

[0052] The training method of the pilot training evaluation model includes:

[0053] Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images;

[0054] Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture;

[0055] Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set;

[0056] The constructed pilot training evaluation model is trained according to the training sample set.

[0057] The embodiment of the present invention solves the problem of low objectivity and poor real-time performance in evaluating pilot training behaviors. By objectively analyzing the actions of pilots, the deviation caused by subjective judgment can be reduced and the accuracy of evaluation can be improved.

[0058] Preferably, in the above embodiment, the human motion image and human motion video are obtained from historical data. It should be noted that during the training process, the pilot uses the reflective ball pasted on the captured flight trainer. When the light emitted by the high-definition camera hits the surface of the reflective ball, the reflective ball will reflect the light of the same wavelength to the camera, and the camera can capture and determine the position of each reflective ball. Specifically, the motion capture technology is used to collect the pilot's motion through its high-definition camera to form a motion image, and the flight trainer's skeleton key points (such as fingers, shoulders, elbows, knees, toes, etc.) and / or 3D motion posture are identified through motion recognition to form a first motion data set. Preferably, the high-definition camera is used to directly shoot the motion information of the training pilot, and then the pilot's human skeleton key points and motion posture are identified through the relevant algorithm module and then converted into motion data through the information to form a first motion data set. Preferably, in the above embodiment, the human motion video of the pilot during the training process is also analyzed for motion posture, and the output is a two-dimensional coordinate to form a second motion data set. After obtaining the above-mentioned first motion data set and second motion data set, the embodiment of the present invention selects relevant standards to mark them to form a standard training sample set to provide data support for subsequent model training.

[0059] Optionally, the above embodiments are formulated using ICAO regulations, CAAC regulations, civil aviation flight manuals and training syllabus requirements and specifications. ICAO, i.e. the International Civil Aviation Organization, is a specialized agency of the United Nations, and its regulations and provisions have an important impact on global civil aviation. CAAC regulations are the China Civil Aviation Regulations. The civil aviation flight manual is an important type of technical document in the field of civil aviation, which aims to provide guidance and specifications on flight operations, maintenance, and operation to aviation professionals such as pilots, maintenance personnel, and dispatchers. The training syllabus requirements and specifications are formulated by different training subjects and are not specifically limited in the embodiments of the present invention.

[0060] In the above embodiment, semantic recognition is performed on the above regulations and specifications to construct a standardized database, so that corresponding standard parameters of flight actions can be extracted in subsequent different pilot training scenarios, so that each training scenario has corresponding standard parameters.

[0061] Furthermore, in the above embodiment, after obtaining an accurate training sample set, the model is trained according to the neural network technology, and the model parameters are adjusted to optimize the performance indicators (such as accuracy, recall rate, F1 score, mean square error, etc.). During the training process, it may be necessary to use cross-validation and other techniques to evaluate the generalization ability of the model and avoid overfitting, which is determined by the actual training process of the model and will not be described in detail here.

[0062] Furthermore, in the above embodiment, in order to quantify the training results of the pilots, the embodiment of the present invention adopts the pilots' competency assessment results for representation. Specifically, the results output by the model include flight time, flight distance, accident rate and time for handling special situations. In addition, other results may also be included, such as deviation, which is used to evaluate the degree of deviation between the pilots' flight attitude or action and the standard. The smaller the deviation, the closer the pilots' flight attitude or action is to the standard; completion, which is used to evaluate the completion of the pilots' operation actions. The higher the completion, the more standardized and accurate the pilots' operations are. Based on whether the pilots can fly the entire flight segment according to the preset flight time and the prescribed pilot duty time in normal or special situations during training. If the flight training task is not completed within the preset flight time and the prescribed pilot duty time, it is judged as unqualified; time index, which can help judge whether the pilots have the ability to react quickly and accurately. The reaction time and action duration of encountering special situations can be set in flight training to evaluate the pilots' time performance in specific operations or actions. If the specific operation or action is not completed within the prescribed time, it is judged as unqualified.

[0063] In the above embodiment, the training output results of each pilot are extracted, including their flight time, flight distance, accident rate, and time for handling special situations as evaluation indicators, and the correlation between various control data and flight safety and flight efficiency is analyzed to obtain a pilot competency index evaluation model, and calculate the competency index score of each pilot. The specific formula is:

[0064] Z I =F T +F D +A I +A C

[0065] Among them, Z I is the pilot competency score, P is the weight coefficient of flight time, Q is the weight coefficient of flight distance, R is the weight coefficient of accident rate, S is the weight coefficient of the time the pilot spends handling special situations during training, and F is the weight coefficient of the flight time. T F is the time for flight training. D is the flight training distance, A I is the incident rate during flight training, A C It refers to the time it takes for pilots to handle special situations during training. Among them, the incident rate during flight training refers to the ratio of various incidents (including accidents, accident signs, unsafe incidents, etc.) occurring within a certain flight training time or a certain number of flight training sorties. This indicator is used to evaluate the safety of flight training activities, as well as the training effect and skill level of pilots. Incident rate = (number of incidents / flight training time or flight training sorties) × 100%. The number of incidents refers to the total number of various incidents occurring within a certain period of time or a certain number of sorties during flight training; flight training time or flight training sorties are used as the denominator to measure the total amount of training activities.

[0066] Since the pilot's training data involves aviation safety, it is necessary to verify the identity information and set the data permissions to ensure the privacy of the data. In the above embodiment, before the training data of the pilot to be evaluated is input into the trained pilot training evaluation model, an identity authentication link is also included. Optionally, the identity information of the pilot to be evaluated is obtained, wherein the identity information at least includes face information, iris information, certificate information and fingerprint information, and then the identity information is security verified.

[0067] In addition, since the pilot training data is confidential data within the air carrier, the calling personnel and identities need to set permissions in order to query the stored data. Therefore, in the initial storage process, the permission instructions bound to the training data of the pilot to be evaluated need to be stored. Different permissions have different functions, for example: administrator identity permissions to perform initial data input, scene adjustment, and overall system debugging of the system; reviewer permissions to obtain training data and generate evaluation training result data; trainer permissions can only be used for training to ensure that flight trainers cannot query and modify training results; transmission permissions can only be used to notify the external interface of the system to transmit training data to the outside.

[0068] Furthermore, in the above embodiment, in order to promote the intelligent process of flight training, the embodiment of the present invention will also generate a matching flight training optimization suggestion log based on the competency assessment results of the pilot to be assessed, wherein the flight training optimization suggestion log includes at least a competency-targeted training plan and a training scenario adjustment plan, so that the trainers and trainees can find out the competency deficiencies in time, adjust the training focus in time, and conduct targeted normative training. In addition, after obtaining the log, the flight training optimization suggestion log can be sent to the mobile terminal of the pilot to be assessed, the cloud server, and the training data middle station respectively.

[0069] For details, see Figure 2 , Figure 2 A structural block diagram of a pilot training evaluation device provided by another embodiment of the present invention is shown, which includes:

[0070] An evaluation module 201, configured to input the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generate a training evaluation result of the pilot to be evaluated based on an output result;

[0071] The training method of the pilot training evaluation model includes:

[0072] Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images;

[0073] Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture;

[0074] Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set;

[0075] The constructed pilot training evaluation model is trained according to the training sample set.

[0076] See also Figure 3 , which is a structural block diagram of a pilot training evaluation device provided in an embodiment of the present invention. The pilot training evaluation device 20 provided in an embodiment of the present invention comprises a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the pilot training evaluation method embodiment described above are implemented, for example Figure 1 Step S101 described in .

[0077] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the pilot training evaluation device 20.

[0078] The pilot training evaluation device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will appreciate that the schematic diagram is merely an example of a pilot training evaluation processing device and does not limit the pilot training evaluation device 20. The pilot training evaluation device 20 may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the pilot training evaluation device 20 may also include input and output devices, network access devices, buses, etc.

[0079] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the pilot training and evaluation device 20, and uses various interfaces and lines to connect various parts of the entire pilot training and evaluation device 20.

[0080] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the pilot training and evaluation device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0081] Wherein, if the module integrated in the pilot training evaluation device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0082] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0083] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the steps in the pilot training evaluation method of the above embodiment, for example Figure 1 Step S101 described in .

[0084] Yet another embodiment of the present invention provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium and is suitable for being read and executed by a processor, so that a computer device having the processor executes the pilot training evaluation method as described above.

[0085] The pilot training assessment method, device, equipment, storage medium, and computer product provided by the embodiments of the present invention have the following beneficial effects:

[0086] (1) The present invention can analyze the data of the pilot training process. By sequentially processing the image data and the video data in a targeted manner, more accurate action features can be obtained, thereby providing accurate data support for the construction of subsequent sample data, and further obtaining a more accurate pilot training evaluation model, thereby avoiding evaluation bias caused by the instructor's subjective experience and promoting the intelligent process of pilot training evaluation.

[0087] (2) By constructing a pilot competency index evaluation relationship, the pilot training results can be quantitatively expressed, thereby providing quantitative support for subsequent recommendations and guidance. For example, targeted training courses can be designed based on the pilot competency evaluation results, and corresponding special flight scenarios can be constructed based on the courses. The flight safety risk behaviors such as pilot fatigue and slow reaction in specific scenarios can be studied, and the correlation between pilot physiological parameters and flight safety can be analyzed, thereby improving the quality of flight training and flight safety.

[0088] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A pilot training evaluation method, characterized in that: include: Inputting the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generating a training evaluation result of the pilot to be evaluated based on the output result; The training method of the pilot training evaluation model includes: Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images; Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture; Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set; The constructed pilot training evaluation model is trained according to the training sample set.

2. The pilot training evaluation method according to claim 1, characterized in that: Before inputting the training data of the pilot to be evaluated into the trained pilot training evaluation model, the method further includes: Acquiring the identity information of the pilot to be evaluated, wherein the identity information includes at least face information, iris information, certificate information and fingerprint information; Perform a security check on the identity information.

3. The pilot training evaluation method according to claim 1, characterized in that: The setting of the standard parameters of the flight action includes: Semantic recognition of ICAO regulations, CAAC regulations, civil aviation flight manuals and training program requirements; Based on the semantic recognition results, a standardized database is constructed; The standard parameters of flight actions corresponding to each training scenario are extracted from the standardized database.

4. The pilot training evaluation method according to claim 1, characterized in that: The output results at least include flight time, flight distance, accident rate and time for handling special situations; The generating the training evaluation result of the pilot to be evaluated based on the output result includes: The flight time, the flight distance, the accident rate and the time for handling special situations are input into a pre-constructed pilot competency index evaluation relationship to obtain a competency evaluation result of the pilot to be evaluated, wherein the pilot competency index evaluation relationship is: Z I =PF T +QF D +UK I +US C Among them, Z I is the pilot competency assessment result, P is the weight coefficient of flight time, Q is the weight coefficient of flight distance, R is the weight coefficient of accident rate, S is the weight coefficient of pilot’s time to handle special situation, F T is the flight time, F D is the flight distance, A I is the event rate, A C Time for handling special situations; The training evaluation result of the pilot to be evaluated is generated based on the competency evaluation result.

5. The pilot training evaluation method according to claim 4, characterized in that: After generating the training evaluation result of the pilot to be evaluated based on the output result, the method further includes: Generate a matching flight training optimization suggestion log according to the competency assessment result of the pilot to be assessed, wherein the flight training optimization suggestion log at least includes a competency-specific training plan and a training scenario adjustment plan; The flight training optimization suggestion log is sent to the mobile terminal of the pilot to be evaluated, the cloud server, and the training data middle station respectively.

6. The pilot training evaluation method according to claim 1, characterized in that: After generating the training evaluation result of the pilot to be evaluated based on the output result, the method further includes: The training data of the pilot to be evaluated is uploaded to a matching database for storage, wherein the storage process is designed to store the authority instruction bound to the training data of the pilot to be evaluated.

7. A pilot training evaluation device, characterized in that: include: An evaluation module, used for inputting the training data of the pilot to be evaluated into a trained pilot training evaluation model, and generating a training evaluation result of the pilot to be evaluated based on an output result; The training method of the pilot training evaluation model includes: Performing action recognition on the human motion images of the pilots during training, to obtain a first action data set consisting of skeleton key points of the pilots in the images; Performing motion posture analysis on the human motion video of the pilot during training, and constructing a second motion data set according to the obtained two-dimensional coordinates corresponding to each key point of each motion posture; Based on preset flight action standard parameters, the first action data set and the second action data set are respectively labeled to obtain a training sample set consisting of the labeled first action data set and the labeled second action data set; The constructed pilot training evaluation model is trained according to the training sample set.

8. A pilot training evaluation device, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the pilot training evaluation method according to any one of claims 1 to 6 is implemented when the processor executes the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the pilot training evaluation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, which is stored in a computer-readable storage medium and is suitable for being read and executed by a processor, so that a computer device having the processor executes the pilot training evaluation method according to any one of claims 1 to 6.

Images