Civil aviation pilot cognitive ability evaluation model weighting system

Abstract

The application relates to a civil aviation pilot cognitive ability evaluation model weighting system, which comprises an evaluation model acquisition unit, which is used for acquiring a civil aviation pilot cognitive ability evaluation model, the evaluation model comprising multiple first-level cognitive ability dimensions, each first-level cognitive ability dimension containing multiple second-level cognitive ability dimensions; a first-level weighting unit, which is used for obtaining weight values of the multiple first-level cognitive ability dimensions by adopting an interval mid-intelligence set method; and a second-level weighting unit, which is used for obtaining question test data of the multiple second-level cognitive ability dimensions, combining the weight values of the multiple first-level cognitive ability dimensions, and obtaining weight values of the multiple second-level cognitive ability dimensions by adopting an entropy weight method. Compared with the prior art, the weighting scheme provided by the application effectively reduces the influence of subjective human factors in the evaluation process, improves the effectiveness of the evaluation model in detecting the cognitive ability of evaluators, and plays an important role in future civil aviation pilot selection and qualification identification and other links.

Description

Technical Field

[0001] This invention relates to the field of aviation safety technology, and in particular to a weighting system for a cognitive ability assessment model for civil aviation pilots. Background Technology

[0002] With the global civil aviation passenger volume increasing year by year, the aviation industry is experiencing rapid development. The speed, high mobility, and good comfort of air transport make it increasingly popular among modern passenger transport modes. However, while transport efficiency has significantly improved, the safety of civil aviation should also receive simultaneous attention. In recent years, with the gradual standardization and high-quality construction of aircraft hardware, the pilot's flying skills and subjective decision-making have become major factors affecting aviation safety. Therefore, accurately assessing and improving pilots' professional qualities and abilities is of great significance for optimizing the safety and reliability of civil aviation.

[0003] The International Air Transport Association (IATA) defines six dimensions for assessing the professional competence of civil aviation pilots: diploma level, English and mathematics proficiency, physics level, basic and complex psychological abilities, personality traits, and operational skills. Compared to basic knowledge and diplomas, cognitive ability, as a crucial component of pilot psychological selection, is closely related to attention, perception, and decision-making abilities, significantly influencing a pilot's operational level, work attitude, and overall performance. However, current industry assessments of cognitive ability in the selection and evaluation of civil aviation pilots are relatively simplistic. A comprehensive, scientifically effective, and industry-recognized evaluation system is needed to improve the overall quality of civil aviation pilots during the selection and evaluation process and enhance the civil aviation flight safety assurance mechanism.

[0004] When assessing the comprehensive cognitive abilities of civil aviation pilots, it is necessary to carefully analyze the specific performance of each cognitive dimension, such as attention, thinking, and perception. Since the importance and influence of each cognitive dimension vary during actual flight operations, the evaluation of each cognitive dimension needs to be weighted and adjusted to ensure that the assessment results are as close as possible to industry realities, thereby improving the accuracy of the comprehensive cognitive assessment.

[0005] The evaluation of the importance of each dimension of a pilot's cognitive ability generally relies heavily on expert review and scoring. However, due to the ambiguity of information inherent in cognitive concepts, the final results obtained by experts using precise scoring based on textual descriptions of the dimensions are not highly reliable. On the other hand, relying solely on expert review and scoring makes the final results significantly influenced by subjective factors. It is highly likely that expert groups responsible for or engaged in different aspects of flight operations will have significantly different levels of emphasis on different cognitive dimensions, which will directly lead to large variations in the weight of each dimension.

[0006] In summary, the current assessment scheme shows that the importance of each dimension of civil aviation pilots' cognitive ability varies, the relationship between the conceptual information contained in cognitive ability and the actual operation is relatively vague, and the results obtained by experts in evaluating the importance of each cognitive dimension are highly subjective and have low certainty. It is necessary to propose a more accurate weighting method to effectively assign weights to each dimension in the assessment model. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the existing technology and provide a weighting system for the cognitive ability assessment model of civil aviation pilots.

[0008] The objective of this invention can be achieved through the following technical solutions:

[0009] A weighting system for a cognitive ability assessment model for civil aviation pilots includes:

[0010] The assessment model acquisition unit is used to acquire a cognitive ability assessment model for civil aviation pilots. The assessment model includes multiple primary cognitive ability dimensions, and each primary cognitive ability dimension contains multiple secondary cognitive ability dimensions.

[0011] The first-level weighting unit is used to obtain the weight values ​​of each first-level cognitive ability dimension using the interval-based intelligence set method;

[0012] The second-level weighted unit is used to obtain the dataset of the cognitive ability assessment test results of civil aviation pilots. Combining the weight values ​​of each first-level cognitive ability dimension, the entropy weight method is used to obtain the weight values ​​of each second-level cognitive ability dimension.

[0013] Furthermore, the first-level weighting unit includes:

[0014] The Interval Moderate Intelligence Language Scale Definition Module is used to define the Interval Moderate Intelligence Language Scale. The Interval Moderate Intelligence Language Scale records the True Moderate Intelligence Interval, False Moderate Intelligence Interval, and Uncertain Moderate Intelligence Interval corresponding to each importance level rating. The importance level rating is used to characterize the relative importance between two primary cognitive ability dimensions.

[0015] The expert scoring module is used to obtain the importance scores of experts for each primary cognitive ability dimension. The importance score is the rating of the importance of one primary cognitive ability dimension relative to other primary cognitive ability dimensions as determined by the Intelligence Language Scale in the reference interval.

[0016] The indicator judgment matrix construction module is used to obtain the importance scores of each primary cognitive ability dimension and generate an indicator judgment matrix. The elements in the indicator judgment matrix are the importance ratings of one primary cognitive ability dimension relative to another primary cognitive ability dimension.

[0017] The interval intelligence set matrix construction module is used to replace the importance rating in the indicator judgment matrix with true intelligence interval, false intelligence interval, and uncertain intelligence interval to obtain the interval intelligence set matrix. The elements in the interval intelligence set matrix are the true intelligence interval, false intelligence interval, and uncertain intelligence interval corresponding to an importance rating.

[0018] The interval intelligence set matrix de-intelligence module is used to transform the true intelligence set interval, false intelligence set interval, and uncertain intelligence set interval of each element in the interval intelligence set matrix into de-intelligence representation values, and obtain the de-intelligence judgment matrix.

[0019] The consistency check module for the decentralization judgment matrix is ​​used to perform consistency checks on the decentralization judgment matrix.

[0020] The interval-based intelligence set matrix normalization processing module is used to normalize the interval-based intelligence set matrix.

[0021] The interval intelligence weight calculation module is used to obtain the interval intelligence weight of each first-level cognitive ability dimension based on the normalized interval intelligence set matrix.

[0022] The weight de-intermediation module is used to de-intermediation the interval intermediation weights of each primary cognitive ability dimension to obtain the weight values ​​of each primary cognitive ability dimension.

[0023] Furthermore, in the interval-based intelligence set matrix de-intelligence module, the conversion of the true intelligence set interval, false intelligence set interval, and uncertain intelligence set interval of each element in the interval-based intelligence set matrix into a single representation value specifically involves:

[0024]

[0025] Among them, U ij Let be the de-intelligentized representation value of the element in the i-th row and j-th column of the intelligence set matrix in the interval. Let it be the lower limit of its true intelligence interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

[0026] Furthermore, in the interval intelligence weight calculation module, the interval intelligence weights for each first-level cognitive ability dimension are obtained specifically based on the normalized interval intelligence set matrix as follows:

[0027]

[0028] Among them, W iLet N be the interval weight of the i-th primary cognitive ability dimension, where n is the number of primary cognitive ability dimensions in the evaluation model. ij These are the elements of the set matrix in the normalized interval.

[0029] Furthermore, in the weight de-intelligence processing module, the de-intelligence processing of the interval weights for each primary cognitive ability dimension specifically involves:

[0030]

[0031] Among them, W i_final This represents the weight value of the i-th primary cognitive ability dimension. Let be the lower limit of the true intelligence interval of the intelligence set in the i-th first-level cognitive ability dimension interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

[0032] Furthermore, in the first-level weighting unit, if the consistency check result of the decentralization intelligent judgment matrix consistency check module is not passed, the importance score is re-obtained by the expert scoring module.

[0033] Furthermore, the secondary weighting unit includes:

[0034] The data standardization processing module is used to obtain the dataset of the cognitive ability assessment test results of civil aviation pilots, and to obtain the scores of all respondents for each question based on the dataset of the assessment test results and to perform standardization processing. Each secondary cognitive ability dimension corresponds to multiple questions, and each question has multiple respondents.

[0035] The information entropy calculation module is used to calculate the information entropy of each secondary cognitive ability dimension;

[0036] The weight calculation module is used to calculate the initial weights of each secondary cognitive ability dimension based on the information entropy of each secondary cognitive ability dimension.

[0037] The weight correction module is used to correct the initial weights of each secondary cognitive ability dimension based on the weight values ​​of the primary cognitive ability dimension to which each secondary cognitive ability dimension belongs, so as to obtain the weight values ​​of each secondary cognitive ability dimension.

[0038] Furthermore, in the information entropy calculation module, the calculation of the information entropy for each secondary cognitive ability dimension is specifically as follows:

[0039]

[0040]

[0041]

[0042] Among them, E ir Let r be the information entropy of the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension. E represents the mean of the information entropy of all questions corresponding to this second-level dimension. irs This represents the information entropy of the s-th question corresponding to the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension, when p irst When = 0, limp irst lnp irst =0, y irst Let m represent the standardized score of the t-th test for the s-th question in the ith primary cognitive dimension, corresponding to the r-th secondary cognitive ability dimension.

[0043] Furthermore, in the weight calculation module, the initial weights of each secondary cognitive ability dimension are calculated using the following formula:

[0044]

[0045] Among them, E ir Let W be the information entropy of the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension. ir Let K represent the initial weight of the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension, and K represent the total number of secondary indicators.

[0046] Furthermore, in the weight correction module, the initial weights of each secondary cognitive ability dimension are corrected as follows:

[0047] W ir_final =W i_final *W ir

[0048] Among them, W i_final W represents the weight value of the i-th primary cognitive ability dimension. ir_final This represents the weight value of the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension after correction.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] (1) This invention provides a weighting scheme based on the IVN-EWM (interval intelligence set-entropy weight method) method. On the basis of ensuring the professionalism of the expert scoring process, the fuzzy range score of the experts is accurately quantified. The results of the real cognitive ability assessment test data are used as the data driving source. The subjective and objective weighting methods are used to reasonably weight various cognitive dimensions and complete the construction of the cognitive ability weighted assessment system for civil aviation pilots.

[0051] (2) The subjective expert review fuzzy scoring method based on the interval-based language scale was adopted for the first-level cognitive ability dimension, which greatly alleviated the negative impact of precise scoring on individual differences in consciousness and improved the accuracy of the final weighting result.

[0052] (3) For the secondary cognitive ability dimension in the assessment model, this invention uses the test scores of real assessment questions as the original data source to form an objective data-driven entropy weighting process. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of the structure of the present invention;

[0054] Figure 2 This diagram illustrates the relationship between cognitive dimensions, test questions, and the scoring mechanism. Detailed Implementation

[0055] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are implemented based on the technical solutions of the present invention, providing detailed implementation methods and specific operating procedures. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them, and the scope of protection of the present invention is not limited to the following embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0056] The term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the invention. In the description of the invention, it should be understood that the terms "first," "second," and "third," etc., in the specification, claims, and accompanying drawings are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0057] Current cognitive ability assessment models for civil aviation pilots, while having established cognitive dimensions and model frameworks, suffer from several drawbacks. These include varying importance of different cognitive ability dimensions among pilots, a relatively ambiguous relationship between conceptual information and practical operational aspects of cognitive ability, and the subjective and unreliable nature of expert evaluations of the importance of each cognitive dimension. To address these issues, this invention proposes a combined subjective and objective weighting method: the IVN-EWM method. This method rationally assigns weights to two levels (Level 1 and Level 2) of cognitive ability dimensions, constructing a weighted assessment model to obtain relatively accurate cognitive ability assessment results for civil aviation pilots.

[0058] To achieve the above functions and objectives, this application provides a weighting system for a cognitive ability assessment model for civil aviation pilots, such as... Figure 1 As shown, it includes:

[0059] (1) Evaluation model acquisition unit, used to acquire the cognitive ability evaluation model of civil aviation pilots. The evaluation model includes multiple primary cognitive ability dimensions, and each primary cognitive ability dimension contains multiple secondary cognitive ability dimensions.

[0060] In this embodiment, the obtained cognitive ability assessment model for civil aviation pilots is as follows: Figure 1 As shown, the model is divided into two dimensional levels, referred to as the first-level cognitive ability dimension and the second-level cognitive ability dimension, with each first-level cognitive ability dimension containing several second-level cognitive ability dimensions.

[0061] Table 1. Assessment Model of Cognitive Ability of Civil Aviation Pilots

[0062]

[0063]

[0064] It is worth noting that this invention focuses on the weighting process of the evaluation model, rather than the selection and establishment of the dimensions of the evaluation model itself. Therefore, the dimensions and framework of the evaluation model selected here are only for reference and can be replaced by other evaluation models with similar structures.

[0065] (2) First-level weighting unit, used to obtain the weight values ​​of each first-level cognitive ability dimension using the interval-based intelligence set method; for each first-level cognitive ability dimension, the IVN (interval-based intelligence set) method is used for weighting. The first-level weighting unit includes:

[0066] (2.1) Interval Medium Intelligence Language Scale Definition Module, used to define the Interval Medium Intelligence Language Scale. The Interval Medium Intelligence Language Scale records the true medium intelligence interval, false medium intelligence interval, and uncertain medium intelligence interval corresponding to each importance level rating. The importance level rating is used to characterize the relative importance between two primary cognitive ability dimensions.

[0067] The Interval-Based Cognitive Language Scale serves as a reference and standard for experts to score the importance of various cognitive dimensions. Similar to language scales in general importance assessment methods, this Interval-Based Cognitive Language Scale also characterizes relative importance based on the relative importance between two assessment elements. In this embodiment, the Interval-Based Cognitive Language Scale includes a total of 11 levels of importance, such as equal importance, absolutely weak importance, very weak importance, and relatively weak importance. Each level of importance rating corresponds to a true moderate intelligence interval, a false moderate intelligence interval, and an uncertain moderate intelligence interval.

[0068] The interval expression for True Wisdom is: Indicates the lower limit of the interval. This represents the upper limit of the interval.

[0069] The expression for the false interval between the two is: Indicates the lower limit of the interval. This represents the upper limit of the interval.

[0070] The expression for the uncertain interval is: Indicates the lower limit of the interval. This represents the upper limit of the interval.

[0071] Table 2 shows an example of the interval-based language scale. It should be noted that the interval-based language scale shown here is only a format example and the content is not the actual content and has no practical significance.

[0072] Table 2 Examples of the representation of the amount of Chinese language in the interval.

[0073]

[0074]

[0075] (2.2) Expert scoring module, used to obtain the importance scores of experts for each primary cognitive ability dimension. The importance score is the rating of the importance of a primary cognitive ability dimension determined by the intelligence language scale in the control interval relative to other primary cognitive ability dimensions.

[0076] After the Interval-Based Intellectual Ability Language Scale definition module is set up, several experts from the civil aviation industry are invited to explain in detail the purpose and methodology of this evaluation and scoring, and to introduce the current framework of the civil aviation pilot cognitive ability assessment model, including its various cognitive dimensions and corresponding textual descriptions. Any questions raised by the experts must be addressed and a consensus reached on-site. Before the evaluation and scoring begin, the Interval-Based Intellectual Ability Language Scale defined in the Interval-Based Intellectual Ability Language Scale definition module must be explained to the experts. After the expert team fully understands the framework, they will complete the importance rating and scoring of the six primary cognitive ability dimensions based on the Interval-Based Intellectual Ability Language Scale.

[0077] (2.3) An indicator judgment matrix construction module, configured to obtain importance scores of respective primary cognitive ability dimensions and generate an indicator judgment matrix, wherein elements in the indicator judgment matrix are importance degree ratings of one primary cognitive ability dimension relative to another primary cognitive ability dimension;

[0078] After the scoring by the expert scoring module is completed, the importance scoring results of the experts are collected and sorted. Two types of results may occur: the first result is that the experts are consistent in the relative importance scores of any two primary cognitive ability dimensions, and the other is that disagreements arise. For the dimension indicators with consistent expert opinions, their corresponding importance degree ratings are directly included in the corresponding positions of the indicator judgment matrix; for the dimension indicators with inconsistent expert opinions, expert review and scoring are re-conducted specifically for these two primary cognitive ability dimensions. If disagreements arise again, a final consistent importance scoring result is obtained after discussion, and the corresponding importance degree rating is included in the corresponding position of the indicator judgment matrix.

[0079] An example of the indicator judgment matrix is shown in Table 3, wherein the symmetric equivalent interval neutrosophic set is abbreviated as N c , for example EI c , it should be noted that the indicator judgment matrix presented here is only a format example, the content is not the actual content and has no practical significance.

[0080] Table 3 Example of indicator judgment matrix

[0081] C1 EI <![CDATA[GI c ]]> <![CDATA[EWI c ]]> C2 GI EI WMI C3 EWI <![CDATA[WMI c ]]> EI

[0082] Matrix processing is performed on the importance degree ratings of the six primary cognitive ability dimensions from the experts to form an indicator judgment matrix, wherein C n etc. represent the n-th primary cognitive ability dimension, and the element at the i-th row and j-th column of the matrix represents the importance level of C i relative to C j .

[0083] (2.4) An interval neutrosophic set matrix construction module, configured to replace the importance degree ratings in the indicator judgment matrix with a truth neutrosophic interval, a falsity neutrosophic interval and an indeterminacy neutrosophic interval, so as to obtain an interval neutrosophic set matrix, wherein elements in the interval neutrosophic set matrix are the truth neutrosophic interval, falsity neutrosophic interval and indeterminacy neutrosophic interval corresponding to one importance degree rating;

[0084] Based on the indicator judgment matrix construction module, each indicator (first-level cognitive ability dimension) has a unified and corresponding importance rating. By referring to the interval intelligence language scale, the importance rating in the indicator judgment matrix is ​​replaced with an interval intelligence set composed of the corresponding true interval intelligence set, false interval intelligence set, and uncertain interval intelligence set, thus forming an interval intelligence set matrix.

[0085] Examples of interval intelligence set matrices are shown in Table 4. It should be noted that the interval intelligence set matrices shown here are only format examples and do not contain actual content, so they have no practical significance.

[0086] Table 4 Examples of Intelligence Set Matrix in Intervals

[0087]

[0088] (2.5) The interval intelligence set matrix de-intelligence module is used to transform the true intelligence set interval, false intelligence set interval, and uncertain intelligence set interval of each element in the interval intelligence set matrix into the de-intelligence representation value, and obtain the de-intelligence judgment matrix.

[0089] Since each element in the current intelligence set matrix consists of three intermediate intelligence intervals, matrix consistency testing is difficult. Therefore, we need to perform an intelligence-removal process on the matrix before testing. The method involves using the intelligence-removal formula proposed by Bolturk to transform the true intermediate interval, false intermediate interval, and uncertain intermediate interval into a single representation value, forming the intelligence-removal judgment matrix. The intelligence-removal formula is:

[0090]

[0091] Among them, U ij Let be the de-intelligentized representation value of the element in the i-th row and j-th column of the intelligence set matrix in the interval. Let it be the lower limit of its true intelligence interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

[0092] (2.6) Consistency check module for decentralization judgment matrix, used to perform consistency check on the decentralization judgment matrix;

[0093] In the interval intelligence set matrix de-intelligentization module, the interval intelligence set matrix is ​​de-intelligentized to obtain the current de-intelligentization judgment matrix. In the de-intelligentization judgment matrix consistency check module, the consistency index CI is first calculated based on the attributes of the de-intelligentization judgment matrix. The calculation formula is as follows:

[0094]

[0095] In the formula λ max is the largest eigenvalue, and o is the matrix order.

[0096] The corresponding average random consistency index RI is then determined by looking up a table. The correspondence between the matrix order and the average random consistency index RI is shown in Table 5.

[0097] Table 5. Correspondence between matrix order and average random consistency index (RI)

[0098] RI 0 0 0.52 0.89 1.12 1.26 1.36 1.41 1.46 1.49

[0099] After determining the average random consistency index RI, the consistency ratio CR is calculated. The formula for calculating CR is:

[0100]

[0101] If CR < 0.1, the consistency of the evidence presented can be considered acceptable; otherwise, the indicator judgment matrix needs to be modified, that is, return to the expert scoring module, reorganize the expert review and scoring, re-score, and then the consistency test is carried out by the indicator judgment matrix construction module, the interval intelligence set matrix construction module, the interval intelligence set matrix de-intelligentization module, and the de-intelligentized judgment matrix consistency test module until the consistency test passes.

[0102] (2.7) The interval-based intelligence set matrix normalization module is used to normalize the interval-based intelligence set matrix. The normalization calculation formula is as follows:

[0103]

[0104] Where, N ij N represents the normalized element of the i-th row and j-th column of the set matrix in the interval. ij It includes normalized intervals for true moderate intelligence, false moderate intelligence, and uncertain moderate intelligence, where i, j = 1, 2, ..., n, and n is the number of first-level cognitive ability dimensions. Let be the lower and upper bounds of the true wisdom interval for the elements in the i-th row and j-th column of the wisdom set matrix in the interval. Let be the lower and upper bounds of the pseudo-intelligent interval for the elements in the i-th row and j-th column of the intelligent set matrix in the interval. Let be the lower and upper bounds of the uncertain interval of the element in the i-th row and j-th column of the set matrix in the interval.

[0105] (2.8) The interval intelligence weight calculation module is used to obtain the interval intelligence weights for each first-level cognitive ability dimension based on the normalized interval intelligence set matrix; the specific calculation formula is as follows:

[0106]

[0107] Among them, W i Let N be the interval weight of the i-th primary cognitive ability dimension, where n is the number of primary cognitive ability dimensions in the evaluation model. ij These are the elements of the set matrix in the normalized interval.

[0108] Since each row of the intelligence matrix in the interval corresponds to a first-level cognitive ability dimension, the interval intelligence weight of each first-level cognitive ability dimension is obtained by calculating the arithmetic mean of each row of the matrix.

[0109] (2.9) The weight removal module is used to remove the intermediate intelligence weights of each primary cognitive ability dimension to obtain the weight values ​​of each primary cognitive ability dimension; the specific calculation formula is as follows:

[0110]

[0111] Among them, W i_final This represents the weight value of the i-th primary cognitive ability dimension. Let be the lower limit of the true intelligence interval of the intelligence set in the i-th first-level cognitive ability dimension interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

[0112] (3) Second-level weighting units are used to obtain the test data of each second-level cognitive ability dimension, and combine the weight values ​​of each first-level cognitive ability dimension with the weight values ​​of each second-level cognitive ability dimension using EWM (Entropy Weight Method). The second-level weighting units include:

[0113] (3.1) Data standardization processing module, used to obtain the dataset of the assessment test results of the civil aviation pilots’ cognitive ability, obtain the scores of all respondents under each question based on the dataset of the assessment test results and perform standardization processing. Among them, there are multiple questions under each secondary cognitive ability dimension, and multiple respondents under each question.

[0114] For the weighting of the secondary cognitive ability dimensions, the entropy weight calculation is based on the dataset of the cognitive ability assessment test results for civil aviation pilots. This test is conducted in the form of test questions, with each secondary cognitive ability dimension associated with several test questions. Participants complete the test questions within a limited time and receive a score for each question. The question format is primarily multiple choice or fill-in-the-blank. Generally, one point is awarded for a correct answer, and no points are awarded for incorrect answers or exceeding the time limit (0-1 scoring system). However, for some dimensions, such as speed estimation, the scoring is not 0-1; instead, points are deducted based on the error between the entered value and the actual answer. The relationship between cognitive dimension, test question, and scoring mechanism is as follows: Figure 2 As shown.

[0115] The design of test questions is not the focus of this invention; the scores of each question in the test are used as the raw data source for the entropy weight method. The design of the corresponding cognitive ability assessment test questions may vary depending on the multi-dimensional cognitive assessment model.

[0116] During the assessment, the s-th question corresponding to the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension can be answered by multiple respondents. Each respondent's score is their score for one assessment session, x. irst It is the original score of the t-th respondent under the s-th question corresponding to the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension, and also the original score of the t-th assessment under the s-th question corresponding to the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension.

[0117] According to the standardization formula, for both 0-1 scoring and non-0-1 scoring questions, the scores of all respondents for each question are standardized using the min-max standardization method. The highest score among all respondents for that question is used as the upper limit, and the lowest score is used as the lower limit. The average score of all questions corresponding to that dimension is then taken as the score for that dimension. The min-max standardization formula is:

[0118]

[0119] In the formula, y irst Let x be the score of the t-th assessment under the s-th question corresponding to the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension after standardization. This is also the score of the t-th respondent under the s-th question corresponding to the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension after standardization. Similarly, x... irst It is the original score of the t-th respondent under the s-th question in the ith-th secondary cognitive ability dimension corresponding to the r-th primary cognitive dimension, minx irstIt is the original score of the lowest score among the t-th respondents for the s-th question in the ith primary cognitive dimension and the r-th secondary cognitive ability dimension, maxx irst It is the original score of the highest scorer among the t-th respondents for the s-th question in the s-th question of the ith-th primary cognitive dimension and the r-th secondary cognitive ability dimension.

[0120] (3.2) Information Entropy Calculation Module, used to calculate the information entropy of each secondary cognitive ability dimension. The specific calculation formula is as follows:

[0121]

[0122]

[0123]

[0124] Among them, E ir Let r be the information entropy of the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension. E represents the mean of the information entropy of all questions corresponding to this second-level dimension. irs This represents the information entropy of the s-th question corresponding to the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension, when p irst When = 0, limp irst lnp irst =0, y irst Let m represent the standardized score of the t-th assessment for the s-th question in the ith primary cognitive dimension, corresponding to the r-th secondary cognitive ability dimension.

[0125] (3.2) The weight calculation module is used to calculate the initial weight of each secondary cognitive ability dimension based on the information entropy of each secondary cognitive ability dimension. The calculation formula is as follows:

[0126]

[0127] Among them, E ir Let W be the information entropy of the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension. ir Let K represent the initial weight of the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension, and K represent the total number of secondary indicators.

[0128] W ir This represents the initial weight of the r-th secondary cognitive ability dimension within the i-th primary cognitive dimension. That is, the initial weight is the weight of the secondary cognitive ability dimension relative to its corresponding primary cognitive ability dimension, rather than the comprehensive weight relative to the entire evaluation model, and therefore needs to be corrected.

[0129] (3.3) The weight correction module is used to correct the initial weights of each secondary cognitive ability dimension based on the weight values ​​of the primary cognitive ability dimensions to which each secondary cognitive ability dimension belongs, thereby obtaining the weight values ​​of each secondary cognitive ability dimension. The specific formula is as follows:

[0130] W ir_final =W i_final *W ir

[0131] Among them, W i_final W represents the weight value of the i-th primary cognitive ability dimension. ir_final This represents the weight value of the r-th secondary cognitive ability dimension in the i-th primary cognitive dimension after correction.

[0132] Multiply the weight value of the first-level cognitive ability dimension by the initial weight of its corresponding second-level cognitive ability dimension to obtain the corrected weight value of the second-level cognitive ability dimension, which is the final weight value of the second-level cognitive ability dimension in the entire evaluation model.

[0133] At this point, the weighting of all dimensions of the civil aviation pilot cognitive ability assessment model has been completed.

[0134] This invention proposes an indicator weighting scheme for a two-level, multi-dimensional assessment model of the cognitive abilities of civil aviation pilots. It breaks the deadlock of subjective weighting that relies solely on expert review and scoring, and the low accuracy and credibility of weighting results for abstract cognitive concepts under the precise scoring model. By combining subjective and objective approaches, it adopts a subjective expert review fuzzy scoring method based on the interval-mode cognitive language scale for the first-level indicators. This greatly alleviates the negative impact of precise scoring on individual differences in consciousness and improves the accuracy of the final weighting results.

[0135] On the other hand, regarding the secondary dimensions in the assessment model, this invention uses the test scores of real assessment questions as the original data source to form an objective data-driven entropy weighting process. The purpose of the test itself is to effectively differentiate the attributes of the test takers; therefore, its scores can largely reflect the differences in the test takers' abilities. In dimensions with low discrimination, it is difficult to have a substantial impact on the final ability assessment. However, the dimensions with high discrimination and their corresponding questions often have a significant impact. The entropy weighting process method is based on this principle and effectively weights the secondary cognitive ability dimensions.

[0136] The empowerment scheme provided in this application effectively reduces the influence of subjective human factors in the evaluation process, improves the effectiveness of the evaluation model in detecting the cognitive abilities of the evaluators, and will play an important role in the selection and qualification assessment of pilots in the future civil aviation industry.

[0137] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A weighting system for a cognitive ability assessment model for civil aviation pilots, characterized in that, include: The assessment model acquisition unit is used to acquire a cognitive ability assessment model for civil aviation pilots. The assessment model includes multiple primary cognitive ability dimensions, and each primary cognitive ability dimension contains multiple secondary cognitive ability dimensions. The first-level weighting unit is used to obtain the weight values ​​of each first-level cognitive ability dimension using the interval-based intelligence set method; The first-level weighting unit includes: The Interval Moderate Intelligence Language Scale Definition Module is used to define the Interval Moderate Intelligence Language Scale. The Interval Moderate Intelligence Language Scale records the True Moderate Intelligence Interval, False Moderate Intelligence Interval, and Uncertain Moderate Intelligence Interval corresponding to each importance level rating. The importance level rating is used to characterize the relative importance between two primary cognitive ability dimensions. The expert scoring module is used to obtain the importance scores of experts for each primary cognitive ability dimension. The importance score is the rating of the importance of one primary cognitive ability dimension relative to other primary cognitive ability dimensions as determined by the Intelligence Language Scale in the reference interval. The indicator judgment matrix construction module is used to obtain the importance scores of each primary cognitive ability dimension and generate an indicator judgment matrix. The elements in the indicator judgment matrix are the importance ratings of one primary cognitive ability dimension relative to another primary cognitive ability dimension. The interval intelligence set matrix construction module is used to replace the importance rating in the indicator judgment matrix with true intelligence interval, false intelligence interval, and uncertain intelligence interval to obtain the interval intelligence set matrix. The elements in the interval intelligence set matrix are the true intelligence interval, false intelligence interval, and uncertain intelligence interval corresponding to an importance rating. The interval intelligence set matrix de-intelligence module is used to transform the true intelligence set interval, false intelligence set interval, and uncertain intelligence set interval of each element in the interval intelligence set matrix into de-intelligence representation values, and obtain the de-intelligence judgment matrix. The consistency check module for the decentralization judgment matrix is ​​used to perform consistency checks on the decentralization judgment matrix. The interval-based intelligence set matrix normalization processing module is used to normalize the interval-based intelligence set matrix. The interval intelligence weight calculation module is used to obtain the interval intelligence weight of each first-level cognitive ability dimension based on the normalized interval intelligence set matrix. The weight de-intermediation module is used to de-intermediation the interval intermediation weights of each primary cognitive ability dimension to obtain the weight values ​​of each primary cognitive ability dimension. The second-level weighted unit is used to obtain the dataset of the cognitive ability assessment test results of civil aviation pilots. Combining the weight values ​​of each first-level cognitive ability dimension, the entropy weight method is used to obtain the weight values ​​of each second-level cognitive ability dimension. The second-level empowerment unit includes: The data standardization processing module is used to obtain the dataset of the cognitive ability assessment test results of civil aviation pilots, and to obtain the scores of all respondents for each question based on the dataset of the assessment test results and to perform standardization processing. Each secondary cognitive ability dimension corresponds to multiple questions, and each question has multiple respondents. The information entropy calculation module is used to calculate the information entropy of each secondary cognitive ability dimension; The weight calculation module is used to calculate the initial weights of each secondary cognitive ability dimension based on the information entropy of each secondary cognitive ability dimension. The weight correction module is used to correct the initial weights of each secondary cognitive ability dimension based on the weight values ​​of the primary cognitive ability dimension to which each secondary cognitive ability dimension belongs, so as to obtain the weight values ​​of each secondary cognitive ability dimension. In the weight correction module, the initial weights of each secondary cognitive ability dimension are corrected as follows: in, Indicates the first The weight values ​​of each primary cognitive ability dimension. Indicates the corrected number The first of the primary cognitive dimensions The weight values ​​of each secondary cognitive ability dimension.

2. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the interval intelligence set matrix de-intelligence module, the true intelligence set interval, false intelligence set interval, and uncertain intelligence set interval of each element in the interval intelligence set matrix are transformed into a single representation value as follows: in, The first element in the set matrix within the interval Line 1 The decentralized representation value of column elements, Let it be the lower limit of its true intelligence interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

3. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the interval intelligence weight calculation module, the interval intelligence weights for each first-level cognitive ability dimension are obtained based on the normalized interval intelligence set matrix as follows: in, For the first The intelligence weights within each primary cognitive ability dimension. To assess the number of primary cognitive ability dimensions in the model, These are the elements of the set matrix in the normalized interval.

4. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the weight removal and de-intelligence processing module, the specific de-intelligence processing of the interval weights for each primary cognitive ability dimension is as follows: in, Indicates the first The weight values ​​of each primary cognitive ability dimension. For the first The lower limit of the true intelligence interval in the intellectual set within each primary cognitive ability dimension interval. Its true intellectual range upper limit, Let it be the lower limit of the false middle-intelligence interval. Let it be the upper limit of the false China-Intelligence interval. The upper limit of its uncertain range.

5. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the first-level weighting unit, if the consistency check result of the decentralization judgment matrix consistency check module is not passed, the importance score is re-obtained by the expert scoring module.

6. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the information entropy calculation module, the information entropy of each secondary cognitive ability dimension is calculated as follows: in, For the first The first of the primary cognitive dimensions Information entropy of each secondary cognitive ability dimension This represents the mean of the information entropy of all questions corresponding to this second-level dimension. Indicates the first The first of the primary cognitive dimensions The first corresponding to the second-level cognitive ability dimension The information entropy of the question, when hour, , Indicates the first The first of the primary cognitive dimensions The first corresponding to the second-level cognitive ability dimension The question is below. The standardized value of the sub-assessment score. Indicates the number of assessments.

7. The weighting system for a civil aviation pilot cognitive ability assessment model according to claim 1, characterized in that, In the weight calculation module, the initial weights of each secondary cognitive ability dimension are calculated using the following formula: in, For the first The first of the primary cognitive dimensions Information entropy of each secondary cognitive ability dimension Indicates the first The first of the primary cognitive dimensions The initial weights of each secondary cognitive ability dimension, This indicates the total number of secondary indicators.

Images