Training quality evaluation method and system based on pilot attention distribution

Abstract

The invention relates to the technical field of operation training evaluation, in particular to a training quality evaluation method and system based on pilot attention distribution. The method comprises the following steps: collecting data required by pilot attention distribution training quality evaluation according to a specific flight mission scene; based on the collected data, calculating a standard attention distribution model of the pilot in a specific flight mission scene, and generating attention distribution and actual attention distribution of the standard attention distribution model; and comparing the attention distribution of the standard attention distribution model with the actual attention distribution, evaluating the training quality of the attention distribution of the pilot in the specific flight mission scene, and forming and displaying an evaluation result. According to the method, the attention distribution mode of the pilot is quantified, the eye movement tracking technology and task-related subjective and objective data are combined, the performance of the pilot in simulator training can be objectively and accurately evaluated, and the scientificity, fairness and safety of flight training are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation training evaluation, and more particularly to a training quality evaluation method and system based on pilot attention allocation. Background Art

[0002] At present, pilot training technology mainly includes traditional ground classroom teaching, flight simulator training and actual flight training. Among them, flight simulator training has become a core component of pilot training due to its high controllability and cost-effectiveness. Flight simulators can reproduce various flight environments and emergency situations for pilots to train under risk-free conditions.

[0003] However, flight simulator-based training programs have always been a major challenge in the field in terms of evaluating the efficiency and effectiveness of flight training. For the evaluation of simulator training flight quality, the current method mainly relies on subjective overall qualitative evaluation, and the evaluation criteria of the simulator training syllabus are also relatively macro. At present, the evaluation of pilot training mainly relies on the instructor's subjective qualitative evaluation, usually by observing the pilot's real-time operation results to evaluate their flight quality on the simulator, which leads to problems such as inconsistent evaluation standards, poor objectivity, and lack of systematic quantitative analysis methods. Therefore, the accuracy and consistency of the evaluation results are difficult to be effectively guaranteed.

[0004] In addition, simulator-based training usually focuses more on pilots' operating skills, but may ignore the attention allocation of pilots when performing specific scenario tasks. Pilots need to monitor multiple task information sources in real time during flight. How to reasonably allocate attention and ensure timely processing of key data has become an important guarantee for flight safety. Neglecting attention allocation may cause pilots to develop the habit of ignoring specific information or observing specific instrument information at inappropriate times, thereby reducing the quality of training and even producing counterproductive effects.

[0005] As flight missions become more complex, pilots need to focus not only on flight operations but also on different instruments, external vision, and changes in flight missions. Therefore, a training quality assessment method for pilot attention allocation patterns is needed. Summary of the invention

[0006] The purpose of the present invention is to provide a training quality assessment method and system based on pilot attention allocation, so as to solve the problem that it is difficult to objectively and accurately assess the training quality of pilot attention allocation in the prior art.

[0007] In order to achieve the above object, the present invention provides a training quality assessment method based on pilot attention allocation, comprising the following steps:

[0008] Data collection steps: Collect the data required for the quality evaluation of pilot attention allocation training based on specific flight mission scenarios;

[0009] Attention allocation model calculation and processing steps: based on the collected data, a standard attention allocation model of the pilot in a specific flight mission scenario is calculated, and the attention allocation of the standard attention allocation model and the actual attention allocation are generated;

[0010] Attention allocation evaluation steps: compare the attention allocation of the standard attention allocation model with the actual attention allocation, evaluate the training quality of the pilot's attention allocation in a specific flight mission scenario, and form and display the evaluation results;

[0011] The construction process of the standard attention allocation model further includes:

[0012] Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest;

[0013] Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated;

[0014] Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

[0015] In some embodiments, in the data collection step, the collected data includes subjective data and objective data of each region of interest in a specific flight mission scenario:

[0016] The subjective data at least includes information expectation and information value;

[0017] The objective data at least includes effort parameter and information salience parameter data.

[0018] In some embodiments, in the data collection step, the collected data includes eye movement data of each area of ​​interest of the pilot in a specific flight mission scenario:

[0019] The eye movement data at least includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest in a specific flight mission scenario.

[0020] In some embodiments, the step of generating the attention allocation of the standard attention allocation model and the actual attention allocation further comprises:

[0021] According to the standard attention allocation model, the predicted attention allocation ratio of each region of interest is calculated;

[0022] Based on the eye movement data, the actual attention allocation ratio of each area of ​​interest is calculated.

[0023] In some embodiments, the step of comparing the attention allocation according to the standard attention allocation model with the actual attention allocation, evaluating the training quality of the pilot's attention allocation in a specific flight mission scenario, and forming an evaluation result further includes:

[0024] Perform a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest;

[0025] The results of regression analysis are used to evaluate the pilots' attention resource allocation during flight tasks.

[0026] In some embodiments, the step of displaying the evaluation results further comprises:

[0027] Visualize the predicted and actual attention allocations for each region of interest; and / or

[0028] The results of regression analysis are presented in a visual way.

[0029] In some embodiments, the step of calculating the actual attention allocation ratio of each region of interest based on the eye movement data further includes:

[0030] According to the pilot's gaze time on each area of ​​interest, the proportion of each area of ​​interest in all areas of interest during the entire flight mission is calculated to obtain the actual attention allocation ratio; or

[0031] According to the number of times the pilot looks at each ROI, the proportion of each ROI to all ROIs during the entire flight mission is calculated to obtain the actual attention allocation ratio.

[0032] In order to achieve the above object, the present invention provides a training quality evaluation system based on pilot attention allocation, including a data collection module, a calculation processing module and a feedback terminal module:

[0033] The data collection module collects data required for the quality assessment of pilot attention allocation training according to a specific flight mission scenario;

[0034] The calculation processing module calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the collected data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result;

[0035] The feedback terminal module is used to display the evaluation results;

[0036] The process of constructing the standard attention allocation model in the calculation processing module further includes:

[0037] Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest;

[0038] Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated;

[0039] Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

[0040] In some embodiments, the data collection module includes a parameter collection unit:

[0041] The parameter collection unit is used to collect subjective data and objective data of each region of interest in a specific flight mission scenario;

[0042] The subjective data at least includes information expectation and information value;

[0043] The objective data at least includes effort parameter and information salience parameter data.

[0044] In some embodiments, the data collection module includes an eye movement data collection unit:

[0045] The eye movement data acquisition unit is used to collect the eye movement data of each area of ​​interest of the pilot in a specific flight mission scenario;

[0046] The eye movement data at least includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest during the flight mission.

[0047] In some embodiments, the computing and processing module includes an eye movement data collection unit and a computing and processing unit:

[0048] The eye movement data collection unit is used to receive the data from the eye movement data acquisition unit and transmit it to the calculation processing unit after pre-processing;

[0049] The computing and processing unit calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the preprocessed data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result.

[0050] In some embodiments, the calculation processing unit calculates objective attention allocation parameters of the region of interest based on the collected objective data of the region of interest;

[0051] The calculation processing unit calculates a subjective attention allocation parameter of the region of interest based on the collected subjective data of the region of interest;

[0052] The calculation processing unit comprehensively calculates the total attention allocation parameter of the pilot based on the objective attention allocation parameter and the subjective attention allocation parameter.

[0053] In some embodiments, the computing processing unit calculates the predicted attention allocation ratio of each region of interest according to a standard attention allocation model;

[0054] The computing and processing unit calculates the actual attention allocation ratio of each region of interest based on the eye movement data.

[0055] In some embodiments, the computing and processing unit performs a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest;

[0056] The computing and processing unit evaluates the pilot's attention resource allocation in the flight mission through the results of regression analysis.

[0057] In some embodiments, the computing unit calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the pilot's gaze duration on each region of interest, and obtains the actual attention allocation ratio; or

[0058] The calculation processing unit calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the number of times the pilot gazes at each region of interest, and obtains the actual attention allocation ratio.

[0059] In some embodiments, the feedback terminal module presents the predicted attention allocation ratio and the actual attention allocation ratio of each region of interest in a visual manner; and / or

[0060] The feedback terminal module displays the results of the regression analysis in a visual manner.

[0061] The present invention provides a training quality assessment method and system based on pilot attention allocation, which can objectively and accurately assess the pilot's performance in simulator training and quickly and efficiently assess the pilot's attention allocation by quantifying the pilot's attention allocation pattern and combining eye tracking technology with subjective and objective data related to the task, thereby improving the traditional subjective assessment method and enhancing the scientificity, fairness and safety of flight training. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The above and other features, properties and advantages of the present invention will become more apparent through the following description in conjunction with the accompanying drawings and embodiments, in which the same reference numerals always represent the same features, wherein:

[0063] Figure 1 A step diagram of a training quality assessment method based on pilot attention allocation according to an embodiment of the present invention is disclosed;

[0064] Figure 2 A principle block diagram of a training quality assessment system based on pilot attention allocation according to an embodiment of the present invention is disclosed.

[0065] The meanings of the reference numerals in the figures are as follows:

[0066] 100 training quality assessment system;

[0067] 110 data collection module;

[0068] 111 parameter collection unit;

[0069] 112 eye movement data acquisition unit;

[0070] 120 computing and processing module;

[0071] 121 computing processing unit;

[0072] 122 eye movement data collection unit;

[0073] 130 Feedback terminal module. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the invention and are not used to limit the invention.

[0075] The present invention proposes a training quality assessment method and system based on pilot attention allocation, which provides relevant information on attention allocation patterns to supplement the assessment of simulator flight training, thereby providing necessary technical support for the development of my country's aviation training field.

[0076] Figure 1 The step diagram of the training quality assessment method based on pilot attention allocation according to an embodiment of the present invention is disclosed, such as Figure 1 As shown, the present invention proposes a training quality assessment method based on pilot attention allocation, comprising the following steps:

[0077] Step S1, data collection: collecting data required for the quality assessment of pilot attention allocation training according to a specific flight mission scenario;

[0078] Step S2, attention allocation model calculation processing: based on the collected data, calculate the standard attention allocation model of the pilot in a specific flight mission scenario, and generate the attention allocation of the standard attention allocation model and the actual attention allocation;

[0079] Step S3, attention allocation evaluation: by comparing the attention allocation of the standard attention allocation model with the actual attention allocation, the training quality of the pilot's attention allocation in a specific flight mission scenario is evaluated, and the evaluation results are formed and displayed.

[0080] The present invention provides a training quality assessment method based on pilot attention allocation, which can quickly and efficiently assess the pilot's attention allocation, improve the traditional subjective assessment method, and enhance the scientificity, fairness and safety of flight training in a quantitative manner.

[0081] These steps will be described in detail below. It should be understood that within the scope of the present invention, the above-mentioned technical features of the present invention and the technical features specifically described below (such as embodiments) can be combined with each other and related to each other to form a preferred technical solution.

[0082] Step S1, data collection: collecting data required for the quality assessment of pilot attention allocation training according to specific flight mission scenarios.

[0083] In this embodiment, the collected data includes subjective data, objective data, and eye movement data of the pilot in each area of ​​interest (AOI) in a specific flight mission scenario.

[0084] Furthermore, the subjective data includes the information expectation and information value of each region of interest in a specific flight mission scenario:

[0085] Information expectation refers to the pilot's expectation of the amount of information provided by an area of ​​interest (AOI) in a specific flight mission.

[0086] Information value refers to the pilot's opinion of the importance of the information provided by the area of ​​interest in the current flight mission.

[0087] In this embodiment, information expectations and information value are collected through subjective scales. Questionnaires or pilot feedback are used to collect this information. Pilots are required to evaluate the information expectations and information value of each AOI and describe their concerns and information needs for these areas.

[0088] Furthermore, the objective data includes the effort parameter and information salience parameter data of the pilot observing the specific area of ​​interest in a specific flight mission scenario:

[0089] The effort parameter refers to the effort the pilot exerts to obtain information about an area of ​​interest.

[0090] Typically, effort is quantified by calculating the distance from a default fixation point using a geometric model. The farther the AOI is from the default fixation point (directly in front of the eyes), the greater the effort the pilot has put in.

[0091] The information salience parameter indicates the information prominence of the AOI, that is, whether the information is easy to identify.

[0092] Factors that affect salience include the AOI symbol design, the contrast between the symbol and the background, and the way information is presented.

[0093] For flight training, the effort parameters and information salience parameters of most AOIs (such as instruments and extravehicular views) should be consistent, because their physical design and position are usually fixed. The effort parameters are because the physical position is close and does not involve raising or lowering the head, and the information salience parameters are because the instrument design of the finished aircraft is perfect by default.

[0094] Furthermore, the eye movement data includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest in a specific flight mission scenario. These data help capture the pilot's attention allocation to different areas during the mission execution, and further compare with the standard attention allocation model.

[0095] Step S2, attention allocation pattern calculation processing: based on the collected data, calculate the standard attention allocation model of the pilot in a specific flight mission scenario, and generate the attention allocation of the standard attention allocation model and the actual attention allocation.

[0096] The collected data needs to be preprocessed, such as denoising and data standardization, to ensure that the data accurately reflects the pilot's actual attention distribution.

[0097] Traditional pilot training evaluation often relies on the subjective judgment of flight instructors, and there may be differences in the scoring standards and evaluation angles between different instructors, resulting in inconsistent evaluation results. The standard attention allocation model proposed in the present invention can eliminate the influence of such subjective factors on the evaluation results, and provide a unified and scientific evaluation standard, which not only improves the evaluation accuracy of flight training quality, but also provides a quantitative basis for subsequent training improvements.

[0098] Furthermore, the construction process of the standard attention allocation model further includes:

[0099] Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest;

[0100] Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated;

[0101] Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

[0102] More specifically, the objective attention allocation parameter can be expressed as an objective attention function;

[0103] In the current flight mission scene, the objective attention function of the visual information of the i-th region of interest , the corresponding expression is:

[0104] ;

[0105] in, is the information prominence of the i-th region of interest;

[0106] is the extra effort the pilot has to make to obtain information about the i-th region of interest by relying on eye movements;

[0107] a and b are the weight coefficients of information salience and effort level, respectively.

[0108] More specifically, the subjective attention allocation parameter can be expressed as a subjective attention function;

[0109] In the current flight mission scene, the subjective attention function of the visual information of the i-th region of interest , the corresponding expression is:

[0110] ;

[0111] in, is the information expectation of the i-th region of interest;

[0112] is the information value of the i-th region of interest;

[0113] c is the weight coefficient of the subjective attention function.

[0114] More specifically, the pilot’s total attention allocation parameter can be expressed as a calculation function of the pilot’s total attention resources;

[0115] In pilot training, factors such as salience, effort, information expectation, and information value jointly affect the allocation of attention resources. By adding these factors, we can get the calculation function of the total attention resources of pilots. , the corresponding expression is:

[0116] ;

[0117] Among them, the pilot's total attention resource calculation function is the total attention resource allocated to the visual information of the i-th region of interest in the current flight mission scene, and f is a constant term.

[0118] The step of generating the attention allocation of the standard attention allocation model and the actual attention allocation further includes:

[0119] According to the standard attention allocation model, the predicted attention allocation ratio of each region of interest is calculated;

[0120] Based on the eye movement data, the actual attention allocation ratio of each area of ​​interest is calculated.

[0121] More specifically, the predicted attention allocation ratio of the i-th region of interest can be expressed as the ratio of the attention resources allocated to the i-th region of interest to the total attention resources , the corresponding expression is:

[0122] ;

[0123] The actual attention allocation is calculated through eye movement data, which is mainly measured by the pilot's gaze duration and number of gazes on different areas of interest (AOI).

[0124] More specifically, the step of calculating the actual attention allocation ratio of each region of interest based on the eye movement data further includes:

[0125] Gaze duration method: According to the pilot's gaze duration on each ROI, the proportion of each ROI in the total ROI during the entire flight mission is calculated to obtain the actual attention allocation ratio; or

[0126] Fixation count method: Based on the number of times the pilot fixates on each ROI, the proportion of each ROI in the entire flight mission is calculated to obtain the actual attention allocation ratio.

[0127] More specifically, the fixation duration method is that the actual attention allocation ratio of the pilot in a certain AOI is equal to the ratio of the fixation duration of a certain AOI to the total fixation duration of all AOIs;

[0128] The fixation time of a certain AOI refers to the total time the pilot stares at the area; the total fixation time of all AOIs refers to the total fixation time of all AOIs during the entire flight mission.

[0129] More specifically, the fixation count method is that the actual attention allocation ratio of the pilot in a certain AOI is equal to the ratio of the fixation count of a certain AOI to the total fixation count of all AOIs;

[0130] The number of fixations on a certain AOI is the number of times the pilot stays on the area, and the total number of fixations on all AOIs is the total number of fixations on all areas by the pilot.

[0131] In order to comprehensively evaluate the pilot's attention allocation, the two indicators of fixation duration and fixation frequency can be combined. Generally, in some complex flight tasks, an AOI with a longer fixation duration may indicate that the pilot is concentrating, while an AOI with a higher fixation frequency may indicate that the pilot is repeatedly reviewing certain information in the area.

[0132] Step S3, attention allocation evaluation: by comparing the attention allocation of the standard attention allocation model with the actual attention allocation, the training quality of the pilot's attention allocation in a specific flight mission scenario is evaluated, and the evaluation results are formed and displayed.

[0133] The attention allocation evaluation step further comprises:

[0134] Perform a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest;

[0135] The results of regression analysis are used to evaluate the pilots' attention resource allocation during flight tasks.

[0136] By comparing the actual attention ratio with the predicted attention ratio in the standard attention allocation model, it is possible to evaluate whether the pilot has allocated his attention effectively, thereby providing feedback on the pilot's performance in training.

[0137] The result of the regression analysis also includes a corresponding fitting function. The purpose of the regression analysis is to find the relationship between the predicted proportion and the actual proportion, and to obtain a fitting function. The fitting function represents the difference between the actual attention allocation of the pilot in a specific flight task and the standard attention allocation model, and reflects the degree of the difference through the regression coefficient.

[0138] The results of regression analysis are used to evaluate whether the pilot's attention resource allocation in the task is reasonable. If the difference between the pilot's actual attention ratio and the predicted attention ratio is large, it means that there is a deviation in the attention allocation in the task execution, which may affect the quality of task execution.

[0139] More specifically, the attention allocation evaluation step further comprises:

[0140] Visualize the predicted and actual attention allocations for each region of interest; and / or

[0141] The results of regression analysis are presented in a visual way.

[0142] In this step, the predicted and actual attention allocation ratios for each area of ​​interest are presented through charts, numbers, or other visualization methods. Differentiated displays are provided to help pilots understand whether their attention allocation is reasonable.

[0143] In this step, the fitting function and fit of the regression analysis are displayed to help pilots and instructors judge the pilot's attention allocation deviation in the task. If the fit is low, it means that the pilot's attention allocation has a large deviation and needs to be improved.

[0144] The training quality assessment method based on pilot attention allocation proposed in this invention combines subjective and objective data, eye tracking technology and standard attention allocation model to comprehensively assess the pilot's attention resource allocation in specific flight tasks. By comparing the standard model with actual data, the training effect of the pilot can be quantified, and targeted feedback and improvement suggestions can be provided to the pilot.

[0145] Figure 2 The principle block diagram of the training quality evaluation system based on pilot attention allocation according to an embodiment of the present invention is disclosed. Figure 2 As shown, a training quality evaluation system 100 based on pilot attention allocation proposed by the present invention includes a data collection module 110, a calculation processing module 120 and a feedback terminal module 130:

[0146] The data collection module 110 collects data required for the quality assessment of pilot attention allocation training according to a specific flight mission scenario;

[0147] The calculation processing module 120 calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the collected data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result;

[0148] The feedback terminal module 130 is used to display the evaluation results.

[0149] Furthermore, the data collection module 110 includes a parameter collection unit 111 and an eye movement data collection unit 112:

[0150] The parameter collection unit 111 is used to collect subjective data and objective data of each region of interest in a specific flight mission scenario;

[0151] The subjective data includes at least the information expectation and information value of each region of interest in a specific flight mission scenario;

[0152] The objective data at least includes the pilot's effort parameter and information salience parameter data when observing a specific area of ​​interest in a specific flight mission scenario.

[0153] More specifically, the parameter collection unit 111 is used to collect parameters required for the calculation processing module to perform calculations under a specific flight mission.

[0154] The parameter collection unit 111 may be in the form of computer software. Through a questionnaire survey, the subjective parameters of flight instructors and senior pilots in a specific flight mission are counted, and these parameters include the information expectation and information value of the interest area of ​​each eye movement fixation point.

[0155] The eye movement data collection unit 112 is used to collect the eye movement data of each area of ​​interest of the pilot in a specific flight mission scenario;

[0156] The eye movement data at least includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest during the flight mission.

[0157] More specifically, the eye movement data collection unit 112 is used to track and collect data such as the subject's gaze trajectory, range, and basic eye movement indicators.

[0158] More specifically, the eye movement data acquisition unit 112 can generally be any eye tracker that can collect the pilot's gaze AOI information during flight training. For example, a Smart Eye eye tracker can be used to collect the pilot's eye movement data.

[0159] The calculation and processing module 120 is used to receive the information data sent by the eye movement data acquisition unit 112, and transmit it to the feedback terminal module 130 after processing and calculation.

[0160] The computing and processing module 120 includes a computing and processing unit 121 and an eye movement data collection unit 122;

[0161] The eye movement data collection unit 122 is used to receive the data from the eye movement data acquisition unit 112 and transmit it to the calculation processing unit 121 after pre-processing;

[0162] In this embodiment, the eye movement data collection unit 122 is in the form of software, and is used to receive data sent by the eye tracker, pre-process the data, etc.;

[0163] The computing processing unit 121 calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the preprocessed data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result.

[0164] In this embodiment, the computing processing unit 121 is in the form of software, which is used to calculate the pre-processed eye movement data collected by the eye movement acquisition module and the subjective and objective data of the flight task collected by the parameter collection module to obtain a standard attention allocation model under a specific flight task.

[0165] The process of constructing the standard attention allocation model by the computing processing unit 121 further includes:

[0166] Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest;

[0167] Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated;

[0168] Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

[0169] Furthermore, the calculation processing unit 121 calculates objective attention allocation parameters of the region of interest based on the collected objective data of the region of interest;

[0170] The calculation processing unit 121 calculates a subjective attention allocation parameter of the region of interest based on the collected subjective data of the region of interest;

[0171] The calculation processing unit 121 comprehensively calculates the total attention allocation parameter of the pilot based on the objective attention allocation parameter and the subjective attention allocation parameter.

[0172] Furthermore, the calculation processing unit 121 calculates the predicted attention allocation ratio of each region of interest according to the standard attention allocation model;

[0173] The calculation processing unit 121 calculates the actual attention allocation ratio of each region of interest based on the eye movement data.

[0174] Furthermore, the calculation processing unit 121 performs a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest;

[0175] The computing and processing unit 121 evaluates the pilot's attention resource allocation in the flight mission through the result of regression analysis.

[0176] Furthermore, the calculation processing unit 121 calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the pilot's gaze duration on each region of interest, and obtains the actual attention allocation ratio; or

[0177] The calculation processing unit 121 calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the number of times the pilot gazes at each region of interest, and obtains the actual attention allocation ratio.

[0178] Other specific calculation steps of the calculation processing unit 121 have been described in detail in the method and will not be repeated here.

[0179] The feedback terminal module 130 is used to display the calculation results transmitted by the calculation processing module 120, and can record data, visualize or issue warnings according to specific needs.

[0180] The feedback terminal module 130 presents the predicted attention allocation ratio and the actual attention allocation ratio of each region of interest in a visual manner; and / or

[0181] The feedback terminal module 130 displays the result of the regression analysis in a visual manner.

[0182] In this embodiment, the feedback terminal module refers to the front-end interface of the software, which is used to display the differences between the actual attention allocation of the pilots under training and the standard attention allocation pattern, as well as the extent of these differences. Data can be recorded, visualized or warnings can be issued according to specific needs.

[0183] The present invention provides a training quality assessment system based on pilot attention allocation, and its corresponding workflow includes multiple steps. The specific contents of these steps can correspond to the process of the aforementioned method, so they are not repeated here.

[0184] The present invention provides a training quality assessment method and system based on pilot attention allocation, which specifically has the following beneficial effects:

[0185] 1) By collecting a small number of key parameters, the attention allocation pattern under a specific flight mission can be quickly calculated. These parameters are generally derived from experienced pilots, and the resulting standard attention allocation model is more in line with actual flight needs and has high authority and reliability. Compared with traditional evaluation methods, the efficiency of data collection and calculation is greatly improved, while reducing the burden of data acquisition;

[0186] 2) By quantifying the allocation of pilots' attention resources during flight missions, the pilots' attention management under specific tasks is converted into quantifiable indicators. By comparing the standard attention allocation pattern with the pilots' attention allocation in actual flight, it can provide objective and scientific data support for evaluating the pilots' performance in simulator training. Compared with the traditional method that relies on the subjective will of flight instructors, it avoids possible deviations and inconsistencies in the evaluation, thereby improving the accuracy of training evaluation.

[0187] Although the above methods are illustrated and described as a series of actions for simplicity of explanation, it should be understood and appreciated that these methods are not limited by the order of the actions, because according to one or more embodiments, some actions may occur in a different order and / or concurrently with other actions from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art.

[0188] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0189] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips cited throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0190] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0191] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in an alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0192] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0193] The above embodiments are provided for persons familiar with the art to implement or use the present invention. Personnel familiar with the art can make various modifications or changes to the above embodiments without departing from the inventive concept of the present invention. Therefore, the protection scope of the present invention is not limited to the above embodiments, but should be the maximum scope of the innovative features mentioned in the claims.

Claims

1. A training quality assessment method based on pilot attention allocation, characterized in that: The following steps are involved: Data collection steps: Collect the data required for the quality evaluation of pilot attention allocation training based on specific flight mission scenarios; Attention allocation model calculation and processing steps: based on the collected data, a standard attention allocation model of the pilot in a specific flight mission scenario is calculated, and the attention allocation of the standard attention allocation model and the actual attention allocation are generated; Attention allocation evaluation step: By comparing the attention allocation of the standard attention allocation model with the actual attention allocation, the training quality of the pilot's attention allocation in a specific flight mission scenario is evaluated, and the evaluation results are formed and displayed; The construction process of the standard attention allocation model further includes: Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest; Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated; Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

2. The training quality assessment method based on pilot attention allocation according to claim 1, characterized in that: In the data collection step, the collected data includes subjective data and objective data of each area of ​​interest in a specific flight mission scenario: The subjective data at least includes information expectation and information value; The objective data at least includes effort parameter and information salience parameter data.

3. The training quality assessment method based on pilot attention allocation according to claim 1, characterized in that: In the data collection step, the collected data includes the eye movement data of each area of ​​interest of the pilot in a specific flight mission scenario: The eye movement data at least includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest in a specific flight mission scenario.

4. The training quality assessment method based on pilot attention allocation according to claim 1, characterized in that: The step of generating the attention allocation of the standard attention allocation model and the actual attention allocation further includes: According to the standard attention allocation model, the predicted attention allocation ratio of each region of interest is calculated; Based on the eye movement data, the actual attention allocation ratio of each area of ​​interest is calculated.

5. The training quality assessment method based on pilot attention allocation according to claim 4, characterized in that: The step of comparing the attention allocation according to the standard attention allocation model with the actual attention allocation, evaluating the training quality of the pilot's attention allocation in a specific flight mission scenario, and forming an evaluation result further includes: Perform a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest; The results of regression analysis are used to evaluate the pilots' attention resource allocation during flight tasks.

6. The training quality assessment method based on pilot attention allocation according to claim 5, characterized in that: The step of displaying the evaluation results further comprises: Visualize the predicted and actual attention allocations for each region of interest; and / or The results of regression analysis are presented in a visual way.

7. The training quality assessment method based on pilot attention allocation according to claim 4, characterized in that: The step of calculating the actual attention allocation ratio of each region of interest based on the eye movement data further includes: According to the pilot's gaze time on each area of ​​interest, the proportion of each area of ​​interest in all areas of interest during the entire flight mission is calculated to obtain the actual attention allocation ratio; or According to the number of times the pilot looks at each ROI, the proportion of each ROI to all ROIs during the entire flight mission is calculated to obtain the actual attention allocation ratio.

8. A training quality assessment system based on pilot attention allocation, characterized in that: Including data collection module, calculation processing module and feedback terminal module: The data collection module collects data required for the quality assessment of pilot attention allocation training according to a specific flight mission scenario; The calculation processing module calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the collected data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result; The feedback terminal module is used to display the evaluation results; The process of constructing the standard attention allocation model in the calculation processing module further includes: Based on the collected objective data of the region of interest, calculating the objective attention allocation parameter of the region of interest; Based on the collected subjective data of the region of interest, a subjective attention allocation parameter of the region of interest is calculated; Based on the objective attention allocation parameters and the subjective attention allocation parameters, the total attention allocation parameters of the pilot are comprehensively calculated.

9. The training quality assessment system based on pilot attention allocation according to claim 8, characterized in that: The data collection module includes a parameter collection unit: The parameter collection unit is used to collect subjective data and objective data of each region of interest in a specific flight mission scenario; The subjective data at least includes information expectation and information value; The objective data at least includes effort parameter and information salience parameter data.

10. The training quality assessment system based on pilot attention allocation according to claim 8, characterized in that: The data collection module includes an eye movement data collection unit: The eye movement data acquisition unit is used to collect the eye movement data of each area of ​​interest of the pilot in a specific flight mission scenario; The eye movement data at least includes the pilot's gaze trajectory, gaze area, eye movement frequency, pupil size and blink frequency data for each area of ​​interest during the flight mission.

11. The training quality assessment system based on pilot attention allocation according to claim 8, characterized in that: The computing and processing module includes an eye movement data collection unit and a computing and processing unit: The eye movement data collection unit is used to receive the data from the eye movement data acquisition unit and transmit it to the calculation processing unit after pre-processing; The computing and processing unit calculates a standard attention allocation model of the pilot in a specific flight mission scenario based on the preprocessed data; generates and compares the attention allocation of the standard attention allocation model with the actual attention allocation, evaluates the training quality of the pilot's attention allocation in the specific flight mission scenario, and forms an evaluation result.

12. The training quality assessment system based on pilot attention allocation according to claim 11, characterized in that: The calculation processing unit calculates the predicted attention allocation ratio of each region of interest according to the standard attention allocation model; The computing and processing unit calculates the actual attention allocation ratio of each region of interest based on the eye movement data.

13. The training quality assessment system based on pilot attention allocation according to claim 12, characterized in that: The computing and processing unit performs a univariate linear regression analysis on the predicted attention allocation ratio and the actual attention ratio of each region of interest; The computing and processing unit evaluates the pilot's attention resource allocation in the flight mission through the results of regression analysis.

14. The training quality assessment system based on pilot attention allocation according to claim 12, characterized in that: The calculation processing unit calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the pilot's gaze duration on each region of interest, and obtains the actual attention allocation ratio; or The calculation processing unit calculates the proportion of each region of interest in all regions of interest during the entire flight mission according to the number of times the pilot gazes at each region of interest, and obtains the actual attention allocation ratio.

15. The training quality assessment system based on pilot attention allocation according to claim 13, characterized in that: The feedback terminal module presents the predicted attention allocation ratio and the actual attention allocation ratio of each region of interest in a visual manner; and / or The feedback terminal module displays the results of the regression analysis in a visual manner.

Images