Method and system for evaluating the post competence of aircraft maintenance personnel

Abstract

The application relates to an aircraft maintenance personnel post competency evaluation method and system. The method comprises the following steps: collecting the post performance archive data (qualification and capacity data, maintenance operation data, examination and evaluation data) of the aircraft maintenance personnel; evaluating the post competency indexes (knowledge level, skill proficiency, work quality, behavior habit and soft skill) of the aircraft maintenance personnel according to the post performance archive data; assigning subjective weights corresponding to each post competency index by using the analytic hierarchy process, and assigning objective weights corresponding to each post competency index by using the entropy weight method; linearly fusing the subjective weights and the objective weights to obtain the comprehensive weights of each post competency index; and comprehensively evaluating the post competency of the aircraft maintenance personnel based on each post competency index and each comprehensive weight through a machine learning model. The scheme provided by the application can solve the problems of one-sidedness, staticity, strong subjectivity and hysteresis in the related art.

Description

Technical Field

[0001] This application relates to the field of aviation maintenance engineering technology, and in particular to methods and systems for assessing the competency of aircraft maintenance personnel. Background Technology

[0002] The competence of aircraft maintenance personnel is a core element in ensuring aircraft airworthiness, maintenance quality, and flight safety.

[0003] In related technologies, the competency assessment methods for aircraft maintenance personnel mainly rely on single data sources such as exam scores, work hour statistics, on-site observation, and subjective ratings by supervisors. These methods have obvious drawbacks: the assessment dimensions are one-sided, the indicator system is static and fixed, the weighting is highly subjective, and the results are delayed and untraceable. They cannot meet the requirements of digital, refined, and intelligent management in civil aviation. Summary of the Invention

[0004] To address or partially address the problems existing in related technologies, this application provides a method and system for evaluating the job competency of aircraft maintenance personnel, which can solve problems such as one-sidedness, static nature, strong subjectivity, and lag in related technologies.

[0005] The first aspect of this application provides a method for assessing the competency of aircraft maintenance personnel, including: Collect performance record data of aircraft maintenance personnel; the performance record data includes qualification and competency data, maintenance operation data, and performance evaluation data; Based on the performance record data, the job competency indicators of the aircraft maintenance personnel are evaluated; the job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills. The Analytic Hierarchy Process (AHP) was used to assign subjective weights to each of the job competency indicators, and the entropy weight method was used to assign objective weights to each of the job competency indicators. The subjective weights and objective weights are linearly fused to obtain the comprehensive weights of each job competency indicator; The machine learning model is used to comprehensively evaluate the job competency of the aircraft maintenance personnel based on the aforementioned job competency indicators and their combined weights.

[0006] In one embodiment, the qualification and competency data includes training and examination records, qualification and retraining records; the maintenance operation data includes maintenance records, electronic work cards, and fault handling records; and the assessment and evaluation data includes quality and safety reports, peer reviews, and error and violation records. The step of evaluating the aircraft maintenance personnel's job competency indicators based on the performance record data includes: The knowledge level of the aircraft maintenance personnel is assessed based on the training and examination records, the qualification and retraining records, and the fault handling records; and... The skill proficiency of the aircraft maintenance personnel is assessed based on the electronic work card, the maintenance record, the fault handling record, and the training and examination record; and, The work quality of the aircraft maintenance personnel is evaluated based on the electronic work card, the maintenance record, the quality and safety report, the error and violation record, and the fault handling record; and... The behavioral habits of the aircraft maintenance personnel are assessed based on the error and violation records, the quality and safety reports, the electronic work cards, the peer reviews, the maintenance records, and the fault handling records; and... The soft skills of the aircraft maintenance personnel are assessed based on the peer reviews, the quality and safety reports, the error and violation records, the electronic work cards, the maintenance records, and the fault handling records.

[0007] In one embodiment, the analytic hierarchy process (AHP) is used to reflect job requirements and industry experience; the AHP is used to assign subjective weights to each of the job competency indicators, including: The importance of each pair of job competency indicators is compared using the 1-9 scale method of the analytic hierarchy process to construct the original judgment matrix for pairwise comparisons of the criteria layer; the criteria layer consists of multiple job competency indicators. The original judgment matrix is ​​normalized column-wise to obtain a normalized matrix; The normalized matrix is ​​summed row by row to obtain a row sum vector; The rows and vectors are normalized to obtain the subjective weights of each of the job competency indicators. The method further includes: Based on the subjective weights of each of the job competency indicators, a consistency check is performed on the original judgment matrix. When the original judgment matrix passes the consistency test, the subjective weights of each of the job competency indicators are determined to be valid.

[0008] In one embodiment, the aircraft maintenance personnel include multiple individuals; the entropy weight method is used to reflect the data distribution characteristics; the process of assigning objective weights to each of the job competency indicators using the entropy weight method includes: Obtain evaluation samples for each of the aforementioned aircraft maintenance personnel; the evaluation samples include scores for each of the aforementioned job competency indicators; The original data matrix is ​​constructed using multiple evaluation samples. The original data matrix is ​​standardized to obtain a standardized matrix; Calculate the weight of each evaluation sample in each of the job competency indicators in the standardized matrix; Based on the weighting of the indicators, calculate the information entropy of each of the job competency indicators. Based on the information entropy, calculate the difference coefficient of each of the job competency indicators; Based on the difference coefficient, the entropy weight of each of the job competency indicators is calculated to obtain the objective weight of each of the job competency indicators.

[0009] In one embodiment, the linear fusion of the subjective weights and the objective weights to obtain the comprehensive weights of each of the job competency indicators includes: Obtain the first level of trust for the subjective weight and the second level of trust for the objective weight; the sum of the first level of trust and the second level of trust is 1, and the first level of trust is less than the second level of trust; The subjective weight, first degree of trust, objective weight, and second degree of trust of each job competency indicator are weighted and summed to obtain the comprehensive weight of each job competency indicator.

[0010] In one embodiment, the job competency is represented by a job competency score; the step of comprehensively evaluating the job competency of the aircraft maintenance personnel using a machine learning model based on each of the job competency indicators and their comprehensive weights includes: Obtain an evaluation sample of the aircraft maintenance personnel; the evaluation sample includes knowledge level score, skill proficiency score, work quality score, behavioral habit score, and soft skills score; The machine learning model is used to perform a weighted summation of the knowledge level score, skill proficiency score, work quality score, behavioral habit score, soft skill score, and the comprehensive weight of each item to obtain the job competency score of the aircraft maintenance personnel.

[0011] In one embodiment, the machine learning model includes a clustering analysis algorithm and a prediction evaluation algorithm; the method further includes: The machine learning model employs the clustering analysis algorithm to classify the aircraft maintenance personnel according to their capabilities; and... The machine learning model employs the prediction and evaluation algorithm to identify skill gaps and provide early warnings of safety risks for aircraft maintenance personnel.

[0012] In one embodiment, the step of using the clustering analysis algorithm through the machine learning model to classify the aircraft maintenance personnel's capabilities includes: If the job competency score is greater than or equal to the first competency threshold, then the aircraft maintenance personnel are classified into the first competency level using the machine learning model; or, If the job competency score is less than the first competency threshold but greater than or equal to the second competency threshold, then the aircraft maintenance personnel are classified into the second competency level using the machine learning model; or, If the job competency score is less than the second competency threshold but greater than or equal to the third competency threshold, the aircraft maintenance personnel will be classified into the third competency level through the machine learning model. Wherein, the first competence threshold > the second competence threshold > the third competence threshold, and the first ability level > the second ability level > the third ability level.

[0013] In one embodiment, the step of using the predictive evaluation algorithm through the machine learning model to identify skill gaps and provide safety risk warnings for the aircraft maintenance personnel includes: The machine learning model identifies job competency indicators whose target scores are lower than the set passing scores as the competency weaknesses in the dimension of the aircraft maintenance personnel; the target score is the product of the score of a single job competency indicator and its corresponding comprehensive weight. Based on the shortcomings in the aforementioned dimension, corresponding risk intervention measures are generated for the aircraft maintenance personnel; the risk intervention measures include at least one of the following: personalized training programs, job matching suggestions, and human resource allocation strategies.

[0014] The second aspect of this application provides a competency assessment system for aircraft maintenance personnel, comprising: The data acquisition module is used to collect performance record data of aircraft maintenance personnel; the performance record data includes qualification and ability data, maintenance operation data, and performance evaluation data. The indicator evaluation module is used to evaluate the job competency indicators of the aircraft maintenance personnel based on the job performance record data; the job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills; The weight assignment module is used to assign subjective weights to each of the job competency indicators using the analytic hierarchy process (AHP) and to assign objective weights to each of the job competency indicators using the entropy weight method. The weight fusion module is used to linearly fuse the subjective weights and the objective weights to obtain the comprehensive weights of each of the job competency indicators; The competency assessment module is used to comprehensively assess the job competency of the aircraft maintenance personnel based on the various job competency indicators and their comprehensive weights using a machine learning model.

[0015] A third aspect of this application provides an electronic device, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0016] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0017] The technical solution provided in this application may include the following beneficial results: The solution provided in this application collects performance record data of aircraft maintenance personnel. This performance record data includes qualification and competency data, maintenance operation data, and performance evaluation data. Based on this data, the solution assesses the job competency indicators of aircraft maintenance personnel. These indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills. The solution employs the analytic hierarchy process (AHP) to assign subjective weights to each job competency indicator and the entropy weight method to assign objective weights. The subjective and objective weights are then linearly fused to obtain the comprehensive weights for each job competency indicator. Finally, a machine learning model is used to comprehensively evaluate the job competency of aircraft maintenance personnel based on these job competency indicators and the comprehensive weights. This application achieves comprehensive evaluation by integrating multi-source performance record data (qualification and capability data, maintenance operation data, and performance evaluation data), achieves dynamic evaluation by using a multi-dimensional job competency indicator system (knowledge level, skill proficiency, work quality, behavioral habits, and soft skills), achieves objectivity evaluation by combining subjective and objective factors, and achieves timeliness and standardization evaluation by using machine learning models. This effectively improves the accuracy of evaluation and meets the requirements of digital, refined, and intelligent management in civil aviation.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0020] Figure 1 This is a flowchart illustrating the competency assessment method for aircraft maintenance personnel as shown in the embodiments of this application; Figure 2This is another flowchart illustrating the aircraft maintenance personnel competency assessment method shown in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the job competency quantitative indicator system shown in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of an aircraft maintenance personnel competency assessment system as shown in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0021] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0022] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0023] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0024] In related technologies, the competency assessment methods for aircraft maintenance personnel mainly rely on single data sources such as exam scores, work hour statistics, on-site observation, and subjective ratings by supervisors. These methods have obvious drawbacks: the assessment dimensions are one-sided, the indicator system is static and fixed, the weighting is highly subjective, and the results are delayed and untraceable. They cannot meet the requirements of digital, refined, and intelligent management in civil aviation.

[0025] To address the aforementioned issues, this application provides a method for assessing the competence of aircraft maintenance personnel. This method achieves comprehensive assessment by integrating multi-source performance record data (qualification and capability data, maintenance operation data, and performance evaluation data), dynamic assessment through a multi-dimensional competency indicator system (knowledge level, skill proficiency, work quality, behavioral habits, and soft skills), objectivity through a combination of subjective and objective weighting, and real-time and standardized assessment through a machine learning model. This effectively improves the accuracy of the assessment and meets the requirements of digital, refined, and intelligent management in civil aviation.

[0026] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart illustrating the competency assessment method for aircraft maintenance personnel as shown in the embodiments of this application.

[0028] See Figure 1 The competency assessment method for aircraft maintenance personnel in this application may include: S110 collects performance record data of aircraft maintenance personnel; the performance record data includes qualification and ability data, maintenance operation data, and performance evaluation data.

[0029] With the widespread adoption of electronic work card systems, training systems, quality and safety management systems, and human resource systems, multi-source heterogeneous data has become collectable, integrateable, and analyzable. Therefore, this application's embodiments construct a complete data-driven, dynamically iterative, objective, accurate, and closed-loop management-based job competency assessment system. This system enables data integration, quantitative modeling, intelligent analysis, visualization, and closed-loop improvement, providing scientific support for aircraft maintenance personnel's job competency management and safety assurance. Thus, the solution provided in this application's embodiments has significant practical implications and application value.

[0030] In the embodiments of this application, it can be applied to the aircraft maintenance personnel job competency assessment system (hereinafter referred to as "this system"). This system communicates and connects with external systems (such as electronic work card system, training system, quality and safety management system, human resources system, etc.) to realize data exchange and linkage.

[0031] In practical applications, when it is necessary to conduct aircraft maintenance personnel competency assessments, identify training needs, provide risk warnings, schedule and allocate personnel, build up talent pools, and manage maintenance safety, an assessment request can be sent to this system. The assessment request carries the identification of the aircraft maintenance personnel so that this system can obtain the performance record data of the aircraft maintenance personnel within a preset time period (such as the past year) based on the identification. The performance record data may include qualification and competency data, maintenance operation data, and assessment and evaluation data.

[0032] The qualification and competency data includes training and examination records, as well as qualification and retraining records, reflecting the certification qualifications and continuous training capabilities of aircraft maintenance personnel. These records are provided by the training system, allowing this system to retrieve them directly. Training and examination records refer to all archival materials generated from on-the-job training, theoretical training, skills practice, safety education, and specialized technical training, along with various theoretical examinations, practical assessment forms, and retake records. These records demonstrate the aircraft maintenance personnel's knowledge acquisition, continuous learning, and training and assessment compliance levels. Qualification and retraining records refer to the essential qualification files for aircraft maintenance personnel, such as initial qualification certificates, licenses, authorization certificates, job qualifications, and legally mandated periodic retraining and qualification maintenance assessment records. These records demonstrate whether the aircraft maintenance personnel possess legal qualifications for their positions, that their qualifications remain valid, and that they have completed qualification maintenance training on schedule.

[0033] Maintenance operation data includes maintenance records, electronic work cards, and fault handling records, reflecting the entire process of aircraft maintenance personnel performing on-site maintenance. Maintenance records and electronic work cards are provided by the electronic work card system, while fault handling records are provided by the quality and safety management system. Therefore, this system can obtain aircraft maintenance personnel's maintenance records and electronic work cards from the electronic work card system, and fault handling records from the quality and safety management system. Maintenance records refer to the written / electronic records generated by aircraft maintenance personnel during all operations including equipment inspection, maintenance, disassembly, assembly, debugging, and scheduled maintenance. These records include maintenance time, maintenance object, maintenance content, maintenance steps, tools used, inspection results, and maintenance signatures, objectively reflecting the actual maintenance frequency, task completion status, and standard compliance of aircraft maintenance personnel. Electronic work cards are digital versions of maintenance worksheets, serving as the basis for executing maintenance tasks. They include maintenance items, maintenance standards, process requirements, measured data, personnel electronic signatures, working hours, and completion confirmation. They record in real-time the tasks undertaken by aircraft maintenance personnel, operational standardization, and the completeness of work card execution, serving as the core data source for the maintenance process. Fault handling records are special records formed after equipment malfunctions or abnormal failures. These records include fault phenomena, fault location, troubleshooting ideas, troubleshooting plans, replaced parts, and verification results. They primarily reflect the fault analysis capabilities, troubleshooting efficiency, and problem-solving effectiveness of aircraft maintenance personnel.

[0034] The assessment data includes quality and safety reports, peer reviews, and error and violation records, which can serve as the basis for evaluating the safety behavior and work performance of aircraft maintenance personnel. The quality and safety reports and error and violation records are provided by the quality and safety management system, while the peer reviews are provided by the human resources system. Therefore, this system can obtain the quality and safety reports and error and violation records of aircraft maintenance personnel from the quality and safety management system, and the peer reviews from the human resources system. The quality and safety reports are quality and safety analysis documents periodically generated by the maintenance unit, covering quality deviations, safety hazards, risk identification, rectification requirements, quality supervision, and verification conclusions in maintenance activities. They include the overall safety and quality situation of the unit and can also trace relevant safety and quality incidents and problems discovered during supervision related to the aircraft maintenance personnel. Peer reviews are mutual evaluations conducted by colleagues in the same work group, in the same position, team leaders, and cooperating aircraft maintenance personnel based on their daily collaborative work performance. Their content typically involves work collaboration ability, communication and cooperation, sense of responsibility, practical cooperation, and risk awareness, and is a qualitative evaluation from a peer's perspective. Error and violation records refer to the registration files of human errors, violations of maintenance specifications, operating procedures, and management systems that occur during the maintenance process. They include descriptions of error events, types of violations, times of occurrence, determination of responsibility, handling measures, and records of rectification and warning education, reflecting the operational risks and compliance level of aircraft maintenance personnel.

[0035] To improve data quality, after collecting various performance record data, this system can first perform preprocessing such as cleaning, deduplication, missing value filling, normalization, and time alignment on the various performance record data to form a standardized evaluation dataset. The standardized evaluation dataset contains the preprocessed performance record data.

[0036] S120 assesses the job competency indicators of aircraft maintenance personnel based on performance record data; job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills.

[0037] This application embodiment pre-constructs a quantitative indicator system for job competency, which covers five dimensions of job competency indicators: knowledge level, skill proficiency, work quality, behavioral habits, and soft skills, so that all indicators are quantifiable, calculable, and verifiable.

[0038] This system can assess the five competency indicators of aircraft maintenance personnel—knowledge level, skill proficiency, work quality, behavioral habits, and soft skills—based on the pre-processed qualification and ability data (training and examination records, qualification and retraining records), maintenance operation data (maintenance records, electronic work cards, fault handling records), and assessment and evaluation data (quality and safety reports, peer reviews, error and violation records) of the personnel, according to the competency indicator system for the position.

[0039] S131 uses the analytic hierarchy process to assign corresponding subjective weights to each job competency indicator.

[0040] The Analytic Hierarchy Process (AHP) is a decision analysis method that combines qualitative and quantitative approaches for multiple criteria and objectives. Its core idea is to break down a complex overall decision objective into objective layer → criterion layer → alternative layer. By comparing the importance of each element pairwise, a judgment matrix is ​​constructed, weights are calculated, and finally, the comprehensive priority weight of each indicator is obtained, thus solving complex decision problems that are difficult to directly quantify and evaluate.

[0041] The Analytic Hierarchy Process (AHP) is a subjective weighting method that relies on the experience of industry experts to make pairwise comparisons. Therefore, this system can use the AHP to assign corresponding subjective weights to each job competency indicator, thereby reflecting the subjective weights of job requirements and industry experience through the AHP.

[0042] S132 uses the entropy weight method to assign corresponding objective weights to each job competency indicator.

[0043] Entropy Weight Method (EWM) originates from thermodynamics. In information theory, information entropy represents the amount of information contained in an indicator. For example, the greater the difference in indicator data, the smaller the entropy value, the more effective information it contains, and the higher the weight. If the indicator data has almost no fluctuation, the entropy value approaches 1, the effective information is less, and the weight is lower.

[0044] Entropy weighting is an objective weighting method that relies on the evaluation sample data of aircraft maintenance personnel to mine the information content of indicators and avoid human subjective bias. Therefore, this system can use entropy weighting to assign corresponding objective weights to each job competency indicator, so as to realize the objective weighting that reflects the data distribution characteristics.

[0045] S140 linearly integrates subjective and objective weights to obtain the comprehensive weight of each job competency indicator.

[0046] To balance the rationality of experience with the objectivity of data, this application adopts a combination of the analytic hierarchy process and the entropy weight method to determine the weights of the indicators, so as to improve the accuracy and stability of the evaluation.

[0047] In its implementation, after obtaining the subjective and objective weights of each job competency indicator, this system linearly integrates these weights to obtain the comprehensive weight w for each job competency indicator. t For example, this system linearly fuses the subjective and objective weights of knowledge level to obtain a comprehensive weight w for knowledge level. t1Furthermore, it linearly integrates the subjective and objective weights of skill proficiency to obtain the comprehensive weight w of skill proficiency. t2 Furthermore, it linearly integrates the subjective and objective weights of work quality to obtain the comprehensive weight w of work quality. t3 Furthermore, the subjective and objective weights of behavioral habits are linearly fused to obtain the comprehensive weight w of the behavioral habits. t4 Furthermore, it linearly integrates the subjective and objective weights of soft skills to obtain the comprehensive weight w of soft skills. t5 .

[0048] S150 uses a machine learning model to comprehensively evaluate the job competency of aircraft maintenance personnel based on various job competency indicators and their overall weights.

[0049] This system can call a pre-deployed machine learning model, and then input all job competency indicators and all comprehensive weights into the machine learning model, so that the machine learning model can conduct in-depth mining based on each job competency indicator and its comprehensive weight, and comprehensively evaluate the job competency of aircraft maintenance personnel.

[0050] It should be noted that the above-mentioned job competency assessment process can be carried out on multiple aircraft maintenance personnel in this application embodiment. For details, please refer to steps S110 to S150 above.

[0051] As can be seen from this example, the solution provided in this application achieves comprehensive evaluation by integrating multi-source performance record data (qualification and capability data, maintenance operation data, and assessment and evaluation data), achieves dynamic evaluation by a multi-dimensional job competency indicator system (knowledge level, skill proficiency, work quality, behavioral habits, and soft skills), achieves objectivity in evaluation by combining subjective and objective factors, and achieves immediacy and standardization in evaluation by using machine learning models. This effectively improves the accuracy of evaluation and meets the requirements of digital, refined, and intelligent management in civil aviation.

[0052] Figure 2 This is another flowchart illustrating the competency assessment method for aircraft maintenance personnel shown in this application.

[0053] See Figure 3 The competency assessment method for aircraft maintenance personnel in this application may include: S210 collects performance record data of aircraft maintenance personnel; the performance record data includes qualification and ability data, maintenance operation data, and performance evaluation data.

[0054] This step can be found in the description in S110, and will not be repeated here.

[0055] S220 assesses the job competency indicators of aircraft maintenance personnel based on performance record data; job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills.

[0056] This application's embodiments pre-construct a multi-dimensional, hierarchical quantitative indicator system for job competency, such as... Figure 3 As shown, this system encompasses five dimensions of job competency indicators: knowledge level (I), skill proficiency (II), work quality (III), behavioral habits (IV), and soft skills (V). All indicators are quantifiable, calculable, and verifiable. Specifically, knowledge level (I) covers theoretical knowledge, aircraft type knowledge, and regulations and standards; skill proficiency (II) covers practical skills, troubleshooting abilities, and work efficiency; work quality (III) covers first-time pass, rework errors, and standardized operations; behavioral habits (IV) covers risk prevention, teamwork, and communication; and soft skills (V) covers safety awareness, sense of responsibility, and responsiveness.

[0057] It should be noted that the job competency indicator system provided in this application embodiment can be continuously updated with new models, new technologies, and new maintenance standards.

[0058] In one implementation, assessing the job competency indicators of aircraft maintenance personnel based on performance record data may include: The knowledge level of aircraft maintenance personnel is assessed based on training and examination records, qualification and retraining records, and fault handling records; the skill proficiency of aircraft maintenance personnel is assessed based on electronic work cards, maintenance records, fault handling records, and training and examination records; the work quality of aircraft maintenance personnel is assessed based on electronic work cards, maintenance records, quality and safety reports, error and violation records, and fault handling records; the behavioral habits of aircraft maintenance personnel are assessed based on error and violation records, quality and safety reports, electronic work cards, peer reviews, maintenance records, and fault handling records; and the soft skills of aircraft maintenance personnel are assessed based on peer reviews, quality and safety reports, error and violation records, electronic work cards, maintenance records, and fault handling records.

[0059] Knowledge level encompasses three aspects: theoretical knowledge, aircraft type knowledge, and regulatory standards. This system can directly evaluate the knowledge level of aircraft maintenance personnel based on training and examination records, qualification and retraining records, and further verify this through fault handling records. Training and examination records cover theoretical, aircraft type, and regulatory-related assessment scores, directly reflecting the degree of knowledge mastery among aircraft maintenance personnel. Qualification and retraining records demonstrate the aircraft maintenance personnel's aircraft type authorization qualifications and the periodic maintenance of their regulatory and professional knowledge. Fault handling records indirectly characterize the aircraft maintenance personnel's ability to apply theory, aircraft type principles, and regulatory standards through fault diagnosis logic and the rationality of troubleshooting solutions.

[0060] Skill proficiency encompasses three aspects: practical skills, troubleshooting ability, and work card efficiency. This system can conduct a comprehensive assessment of aircraft maintenance personnel's skill proficiency based on electronic work cards, maintenance records, fault handling records, and training and examination records. Specifically, electronic work cards are used to track the time spent on procedures and the completion status of tasks, measuring work card efficiency; maintenance records reflect the participation of aircraft maintenance personnel in various maintenance tasks, demonstrating long-term practical skills; fault handling records evaluate the troubleshooting ability of aircraft maintenance personnel through fault isolation efficiency and troubleshooting success rate; and practical assessment scores in training and examination records can serve as supplementary references for the basic skill level of aircraft maintenance personnel.

[0061] Work quality encompasses three aspects: first-time completion, rework errors, and standardized operations. This system can conduct a comprehensive assessment of aircraft maintenance personnel's work quality based on electronic work cards, maintenance records, quality and safety reports, error and violation records, and fault handling records. Specifically, electronic work cards and maintenance records are used to statistically analyze the percentage of maintenance tasks completed on the first attempt and the frequency of rework, measuring the first-time completion level; error and violation records and quality and safety reports record defects, violations, and quality issues in the maintenance process, reflecting the implementation of rework errors and standardized operations; and fault handling records, through the recurrence of faults after maintenance, help determine whether the aircraft maintenance personnel's maintenance quality meets the standards.

[0062] Behavioral habits encompass three aspects: risk prevention, teamwork, and communication. This system can conduct a comprehensive assessment of the behavioral habits of aircraft maintenance personnel based on error and violation records, quality and safety reports, electronic work cards, peer reviews, maintenance records, and fault handling records. Among these, error and violation records, quality and safety reports, and electronic work cards primarily reflect the risk prevention awareness and compliance habits of aircraft maintenance personnel during operations; peer reviews serve as the core basis for evaluating teamwork and communication abilities; and maintenance records and fault handling records, through the collaborative task execution and fault information transmission, further verify the level of teamwork and communication.

[0063] Soft skills encompass three aspects: safety awareness, sense of responsibility, and responsiveness. This system can conduct a comprehensive assessment of aircraft maintenance personnel's soft skills based on peer reviews, quality and safety reports, error and violation records, electronic work cards, fault handling records, and maintenance records. Peer reviews serve as the core qualitative basis for evaluating aircraft maintenance personnel's sense of responsibility and work responsiveness; error and violation records and quality and safety reports are used to identify issues such as insufficient safety awareness and inadequate performance of duties; electronic work cards, fault handling records, and maintenance records, through task closure, fault response, and operational details, further corroborate the aircraft maintenance personnel's sense of responsibility and proactive work attitude.

[0064] S231 uses the analytic hierarchy process to assign corresponding subjective weights to each job competency indicator.

[0065] This step can be found in the description in S131, and will not be repeated here.

[0066] In one implementation, the Analytic Hierarchy Process (AHP) is used to reflect job requirements and industry experience; the AHP is used to assign corresponding subjective weights to each job competency indicator, which may include: The 1-9 scale method of the analytic hierarchy process (AHP) is used to compare the importance of each pair of job competency indicators to construct the original judgment matrix for pairwise comparisons at the criterion level. The criterion level consists of multiple job competency indicators. The original judgment matrix is ​​normalized column-wise to obtain a normalized matrix. The normalized matrix is ​​then summed row-wise to obtain a row sum vector. The row sum vector is then normalized to obtain the subjective weights of each job competency indicator.

[0067] It should be noted that the subjective scoring relied upon in the related technologies and the analytic hierarchy process adopted in the embodiments of this application both belong to subjective weighting. However, the related technologies involve direct subjective scoring (experts directly assign weights), which has a great deal of arbitrariness. The analytic hierarchy process in the embodiments of this application imposes logical constraints on expert judgments through pairwise comparison scales and consistency tests, so that the qualitative judgments of expert experience are transformed into quantitative weights, thereby effectively reducing the arbitrariness of the assignment.

[0068] In its implementation, this system constructs a hierarchical model, encompassing an objective layer, a criterion layer, and a solution layer (optional; if only indicator weights are required, the solution layer can be omitted). The objective layer represents the job competencies of aircraft maintenance personnel; the criterion layer includes knowledge level (C1), skill proficiency (C2), work quality (C3), behavioral habits (C4), and soft skills (C5). Based on industry expert consensus (job requirements and industry experience), this system ranks all job competency indicators by importance, assuming the ranking is: skill proficiency > work quality > knowledge level > behavioral habits > soft skills. The system employs the 1-9 scale method of the Analytic Hierarchy Process (AHP) to compare the importance of each pair of job competency indicators, constructing the original judgment matrix A for pairwise comparisons at the criterion layer. It should be noted that the 1-9 scale method of the Analytic Hierarchy Process (AHP) is as follows: scale 1 represents that two elements are equally important, scale 3 represents that the former is slightly more important than the latter, scale 5 represents that the former is significantly more important than the latter, scale 7 represents that the former is strongly more important than the latter, scale 9 represents that the former is extremely more important than the latter, and scales 2 / 4 / 6 / 8 represent the intermediate values ​​of the above adjacent levels. Based on this, the original judgment matrix A can be constructed as follows: The matrix rules are as follows: The diagonal is always 1, and the row and column indicators are C1, C2, C3, C4, and C5 respectively. This system can use the summation method to solve the original judgment matrix A, obtaining the subjective weight w for each job competency indicator. ci Specifically, firstly, this system normalizes the original judgment matrix A column-wise to obtain the normalized matrix A': Then, the system performs row-wise summation on the normalized matrix A to obtain the row sum vector S: Next, the system normalizes the row and vector S to obtain the weight vector S': The weight vector S' contains the subjective weights w of each job competency indicator. c Subjective weighting of knowledge level w c1 The subjective weight w for skill proficiency is 0.163. c2 The subjective weight w for work quality is 0.426. c3 The subjective weight w of behavioral habits is 0.269. c4 The subjective weight w for soft skills is 0.092. c5 It is 0.05.

[0069] In one embodiment, the method may further include: Based on the subjective weights of each job competency indicator, a consistency test is performed on the original judgment matrix; when the original judgment matrix passes the consistency test, the subjective weights of each job competency indicator are deemed valid.

[0070] To avoid logical contradictions in expert judgments, this system performs a consistency check on the original judgment matrix A. When the judgment matrix passes the consistency check, the subjective weight w calculated above is determined. c If it is effective, then proceed to step S240.

[0071] In the specific implementation, firstly, this system calculates the product Aw of the original judgment matrix A and the weight vector S': This allows for the calculation of the product Aw and the subjective weights w of each job competency indicator. c Calculate the largest eigenvalue λ max :λ max =5.093; then, this system is based on the largest eigenvalue λ maxBased on the order n (n=5) of the original judgment matrix A, the consistency index CI is calculated: CI=0.023. Furthermore, based on the order n (n=5) of the original judgment matrix A, the system determines the random consistency index RI: RI=1.12. Subsequently, the system calculates the ratio of the consistency index CI to the random consistency index RI, obtaining the consistency ratio CR: CR=0.021. Since the consistency ratio CR < 0.1, the original judgment matrix A is deemed to have passed the consistency test, indicating that the original judgment matrix A is logically sound and the weight vector S' is effective.

[0072] S232 uses the entropy weight method to assign corresponding objective weights to each job competency indicator.

[0073] This step can be found in the description in S132, and will not be repeated here.

[0074] In one embodiment, the aircraft maintenance personnel include multiple individuals; the entropy weight method is used to reflect the data distribution characteristics; the entropy weight method is used to assign corresponding objective weights to each job competency indicator, which may include: The evaluation samples of each aircraft maintenance worker are obtained; the evaluation samples include scores for various job competency indicators; an original data matrix is ​​constructed using multiple evaluation samples; the original data matrix is ​​standardized to obtain a standardized matrix; the weight of each evaluation sample in each job competency indicator in the standardized matrix is ​​calculated; based on the indicator weight, the information entropy of each job competency indicator is calculated; based on the information entropy, the difference coefficient of each job competency indicator is calculated; based on the difference coefficient, the entropy weight of each job competency indicator is calculated to obtain the objective weight of each job competency indicator.

[0075] Aircraft maintenance personnel may be multiple; this embodiment uses four aircraft maintenance personnel as an example for illustration. The system obtains evaluation samples for each aircraft maintenance personnel through step S220 above. These evaluation samples include scores for each job competency indicator (such as knowledge level score, skill proficiency score, work quality score, behavioral habits score, and soft skills score). The system uses these evaluation samples to construct the original data matrix X: In this matrix, rows represent evaluation samples, and columns represent job competency indicators: knowledge level (X1), skill proficiency (X2), work quality (X3), behavioral habits (X4), and soft skills (X5). Subsequently, the system standardizes the original data matrix X to obtain the standardized matrix Y. This system sums the standardized matrix Y column by column to obtain the sum of each column, and then calculates the ratio P of each element in each column to the sum of its column. ij The ratio P ij This represents the weight of a single evaluation sample in a single job competency indicator, resulting in the indicator weight matrix P: In this matrix, each element of the indicator weight matrix P represents the weight of each evaluation sample in each job competency indicator. ij Then, based on the weighting of the four indicators corresponding to each job competency indicator in the indicator weighting matrix P and combined with the sample size m (m=4), this system calculates the information entropy e of each job competency indicator. j The information entropy e1 for knowledge level is 0.699, for skill proficiency e2 it is 0.777, for work quality e3 it is 0.7, for behavioral habits e4 it is 0.773, and for soft skills e5 it is 0.747. This system is based on the information entropy e of each job competency indicator. j Calculate the coefficient of variation g for each job competency indicator. j The coefficients of variation for knowledge level (g1) are 0.301, skill proficiency (g2) is 0.223, work quality (g3) is 0.3, behavioral habits (g4) is 0.227, and soft skills (g5) is 0.253. This system can be based on the coefficients of variation for each job competency indicator. j Calculate the entropy weight w for each job competency indicator. x Entropy weight of knowledge level w x1 The entropy weight w of skill proficiency is 0.268. x2 The entropy weight w of the work quality is 0.199. x3 The entropy weight w of behavioral habits is 0.267. x4 The entropy weight w of soft skills is 0.041. x5 The value is 0.225. Entropy weight w xj This refers to objective weighting; therefore, this system assigns an entropy weight w to each job competency indicator. x The output is the objective weight of each job competency indicator.

[0076] This system can rank the objective weights calculated above, resulting in the following ranking: Knowledge Level > Work Quality > Skill Proficiency > Soft Skills > Behavioral Habits. It is evident that the sample scores for Knowledge Level and Work Quality show greater differences, lower information entropy, and larger coefficients of variation, thus resulting in higher entropy weights (objective weights). Conversely, the sample scores for Behavioral Habits are more concentrated, exhibiting weaker differentiation, and thus have the lowest entropy weights (objective weights). This objectively demonstrates that entropy weights (objective weights) are entirely determined by the distribution characteristics of the sample data, effectively avoiding the expert subjective bias problem inherent in the analytic hierarchy process.

[0077] S240 linearly integrates subjective and objective weights to obtain the comprehensive weight of each job competency indicator.

[0078] This step can be found in the description in S140, and will not be repeated here.

[0079] In one implementation, subjective and objective weights are linearly fused to obtain the comprehensive weights for each job competency indicator, which may include: Obtain the first degree of trust for subjective weights and the second degree of trust for objective weights; the sum of the first degree of trust and the second degree of trust is 1, and the first degree of trust is less than the second degree of trust; the subjective weight, first degree of trust, objective weight and second degree of trust of each job competency indicator are weighted and summed to obtain the comprehensive weight of each job competency indicator.

[0080] The embodiments of this application can pre-set a first level of trust based on subjective weight. The second degree of trust in objective weighting ,in, and All are positive integers. Since the Analytic Hierarchy Process (AHP) can introduce expert subjective bias issues, the embodiments of this application can set... .

[0081] This system calculates the subjective weight w for each job competency indicator separately. c and objective weight w x Then, obtain the first level of trust set above. Second level of trust In order to assign subjective weights to each job competency indicator. c First level of trust Objective weight w x Second level of trust We perform a weighted summation to obtain the overall weight w for each job competency indicator. t : .

[0082] For example, suppose , Then the first level of trust is adopted. Second level of trust Regarding the aforementioned subjective weight w c and objective weight w x Linear fusion is performed to obtain the comprehensive weight w for each job competency indicator. t : The overall weight of knowledge level w t1 :w t1 =0.2×0.163+0.8×0.268=0.247; The overall weight of skill proficiency w t2 :w t2 =0.2×0.429+0.8×0.199=0.245; Overall weight of work quality wt3 :w t3 =0.2×0.269+0.8×0.267=0.267; Overall weight of behavioral habits w t4 :w t4 =0.2×0.092+0.8×0.041=0.051; The overall weight of soft skills w t5 :w t5 =0.2×0.05+0.8×0.225=0.190.

[0083] This system can sort the comprehensive weights calculated above, and the index ranking results are as follows: work quality > knowledge level > skill proficiency > behavioral habits > soft skills.

[0084] S250 uses a machine learning model to comprehensively evaluate the job competency of aircraft maintenance personnel based on various job competency indicators and their overall weights.

[0085] This step can be found in the description in S150, and will not be repeated here.

[0086] In one implementation, job competency is represented by a job competency score; the job competency of aircraft maintenance personnel is comprehensively evaluated using a machine learning model based on various job competency indicators and their overall weights, which may include: An evaluation sample of aircraft maintenance personnel was obtained. The evaluation sample included scores on knowledge level, skill proficiency, work quality, behavioral habits, and soft skills. The knowledge level score, skill proficiency score, work quality score, behavioral habits score, soft skills score, and the comprehensive weight of each component were weighted and summed using a machine learning model to obtain the job competency score of the aircraft maintenance personnel.

[0087] Each aircraft maintenance worker's job competency is represented by a job competency score. This application uses an aircraft maintenance worker as an example: the system obtains an evaluation sample of the worker. As mentioned earlier, the evaluation sample includes scores for each job competency indicator (such as knowledge level score, skill proficiency score, work quality score, behavioral habits score, and soft skills score). The system can calculate the knowledge level score and its comprehensive weight w using a machine learning model. t1 The product of these factors yields the first overall score for the aircraft maintenance personnel (knowledge level score × w). t1 ), and calculate skill proficiency scores and their overall weights w t2 The product of these factors yields the second comprehensive score for the aircraft maintenance personnel (skill proficiency score × w). t2 ), and calculate the work quality score and its overall weight w t3The product of these factors yields the third comprehensive score for the aircraft maintenance personnel (work quality score × w). t3 ), and calculate behavioral habit scores and their overall weights w t4 The product of these factors yields the fourth comprehensive score for the aircraft maintenance personnel (behavioral habit score × w). t4 ), and calculate soft skills scores and their overall weights w t5 The product of these factors yields the fifth overall score for the aircraft maintenance personnel (soft skills score × w). t5 Then, add the first, second, third, fourth, and fifth comprehensive scores together to obtain the aircraft maintenance personnel's job competency score: Job Competency Score = Knowledge Level Score × w t1 +Skill proficiency score × w t2 +Work quality score × w t3 +Behavioral habit score × w t4 +Soft skills score × w t5 .

[0088] For example, suppose the evaluation sample of an aircraft maintenance worker has the following scores: knowledge level score of 72, skill proficiency score of 80, work quality score of 75, behavioral habits score of 85, and soft skills score of 76. Then the job competency score of the aircraft maintenance worker is 72×0.247+80×0.245+75×0.267+85×0.051+76×0.19=76.184.

[0089] It should be noted that all the numerical results obtained from the above calculations are for illustrative purposes only.

[0090] S261 uses a machine learning model and clustering analysis algorithm to classify the capabilities of aircraft maintenance personnel.

[0091] In one embodiment, classifying aircraft maintenance personnel by using a clustering analysis algorithm through a machine learning model may include: If the job competency score is greater than or equal to the first competency threshold, the aircraft maintenance personnel are classified into the first competency level using a machine learning model; or, if the job competency score is less than the first competency threshold but greater than or equal to the second competency threshold, the aircraft maintenance personnel are classified into the second competency level using a machine learning model; or, if the job competency score is less than the second competency threshold but greater than or equal to the third competency threshold, the aircraft maintenance personnel are classified into the third competency level using a machine learning model; wherein, the first competency threshold > the second competency threshold > the third competency threshold, and the first competency level > the second competency level > the third competency level.

[0092] The machine learning model incorporates a clustering analysis algorithm, enabling it to classify the capabilities of each aircraft maintenance worker using clustering analysis. This embodiment uses an aircraft maintenance worker as an example: after assessing the worker's job competency score, the machine learning model compares this score with competency thresholds (such as a first competency threshold, a second competency threshold, and a third competency threshold) to classify the worker's capabilities based on the comparison results. The competency thresholds can include the first, second, and third competency thresholds, with the first threshold > the second threshold > the third threshold. Similarly, the capability levels can include a first capability level, a second capability level, and a third capability level, with the first capability level > the second capability level > the third capability level.

[0093] If the job competency score is greater than or equal to the first competency threshold, it indicates that the aircraft maintenance personnel has excellent overall ability, and the machine learning model can classify the aircraft maintenance personnel into the first competency level. If the second competency threshold is less than or equal to the job competency score and less than the first competency threshold, it indicates that the aircraft maintenance personnel has moderate overall ability, and the machine learning model can classify the aircraft maintenance personnel into the second competency level. If the third competency threshold is less than or equal to the job competency score and less than the second competency threshold, it indicates that the aircraft maintenance personnel has poor overall ability, and the machine learning model can classify the aircraft maintenance personnel into the third competency level.

[0094] It should be noted that the embodiments of this application can set more competency thresholds and capability levels according to actual conditions.

[0095] S262 uses machine learning models and predictive evaluation algorithms to identify skill gaps and provide early warnings of safety risks for aircraft maintenance personnel.

[0096] In one embodiment, using the predictive evaluation algorithm through a machine learning model to identify skill gaps and provide safety risk warnings for aircraft maintenance personnel may include: The machine learning model identifies job competency indicators whose target scores are lower than the set passing scores as the competency gaps in the aircraft maintenance personnel's respective dimensions. The target score is the product of the score of a single job competency indicator and its corresponding comprehensive weight. Based on the competency gaps in the respective dimensions, corresponding risk intervention measures are generated for the aircraft maintenance personnel. The risk intervention measures include at least one of the following: personalized training programs, job matching suggestions, and human resource allocation strategies.

[0097] Due to the aforementioned defects in related technologies (one-sided assessment dimensions, static and rigid indicator systems, highly subjective weight assignment, and lagging and untraceable results), it is difficult to achieve capability gap identification, security risk warning, and personalized training delivery.

[0098] The machine learning model in this embodiment incorporates a predictive evaluation algorithm. This algorithm allows the machine learning model to identify skill gaps and provide safety risk warnings for each aircraft maintenance worker, thereby enabling appropriate risk intervention and shifting from descriptive to predictive assessment. This embodiment uses an aircraft maintenance worker as an example: the machine learning model can obtain the target score for each job competency indicator of the aircraft maintenance worker. The target score is the product of the score of each job competency indicator and its corresponding comprehensive weight. Specifically, the target score can be one of five comprehensive scores: a first comprehensive score, a second comprehensive score, a third comprehensive score, a fourth comprehensive score, and a fifth comprehensive score. The machine learning model can compare the target score for each job competency indicator with a set passing score to identify skill gaps for the aircraft maintenance worker based on the comparison results.

[0099] If the target score for a certain job competency indicator is greater than or equal to the set passing score, it indicates that the aircraft maintenance personnel have a good (excellent / average) ability in that job competency indicator and no weaknesses. If the target score for a certain job competency indicator is less than the set passing score, it indicates that the aircraft maintenance personnel have a poor ability in that job competency indicator and have weaknesses. In this case, the machine learning model can identify that job competency indicator as the aircraft maintenance personnel's weakness in that dimension. Based on this weakness, the model can generate corresponding risk intervention measures for the aircraft maintenance personnel. These risk intervention measures may include, but are not limited to, personalized training programs, job matching suggestions, and human resource allocation strategies.

[0100] For example, a certain aircraft maintenance worker has a target score of 17.784 for knowledge level (first comprehensive score), 19.6 for skill proficiency (second comprehensive score), 20.025 for work quality (third comprehensive score), 4.335 for behavioral habits (fourth comprehensive score), and 14.44 for soft skills (fifth comprehensive score). Assuming a passing score of 10, the aircraft maintenance worker's target score for behavioral habits is less than the passing score, while the target scores for other job competency indicators are greater than or equal to the passing score. Therefore, the machine learning model determines that the aircraft maintenance worker has a capability deficiency in the behavioral habits dimension, so as to generate risk intervention measures for the aircraft maintenance worker's behavioral habits (such as personalized training programs, job matching suggestions, human resource allocation strategies, etc.).

[0101] The embodiments of this application can construct a competency profile of aircraft maintenance personnel and visualize it based on the assessment results (job competency score, ability level, and ability shortcomings) and related risk intervention measures. For example, it can establish an individual competency radar chart, a team competency distribution chart, a trend curve, and an early warning dashboard to achieve intuitive display and multi-dimensional query of assessment results.

[0102] The embodiments of this application can establish a closed-loop management mechanism of "assessment-feedback-intervention-improvement": after outputting corresponding risk intervention measures (such as personalized training programs, job matching suggestions, human resource allocation strategies, etc.) based on the assessment results, the effectiveness of aircraft maintenance personnel using the risk intervention measures can be tracked, relevant data can be continuously collected and the machine learning model can be iteratively updated to form a dynamic optimization closed loop.

[0103] As can be seen from this example, the solution provided in this application achieves comprehensive assessment by integrating multi-source performance record data (qualification and capability data, maintenance operation data, and performance evaluation data), dynamic assessment by a multi-dimensional job competency indicator system (knowledge level, skill proficiency, work quality, behavioral habits, and soft skills), objective assessment by combining subjective and objective assessments, real-time, standardized, and predictive assessment by machine learning models, intuitive assessment by visualizing competency profiles, and continuous assessment by a closed-loop management mechanism. This effectively improves the accuracy of assessments, the relevance of training, and the effectiveness of risk control, promoting the transformation of aviation maintenance human resource management towards data-driven intelligence and meeting the requirements of digital, refined, and intelligent management in civil aviation.

[0104] Corresponding to the aforementioned application function implementation method embodiments, this application also provides an aircraft maintenance personnel job competency assessment system, electronic equipment, and corresponding embodiments.

[0105] Figure 4 This is a schematic diagram of the structure of an aircraft maintenance personnel competency assessment system as shown in an embodiment of this application.

[0106] See Figure 4 The aircraft maintenance personnel competency assessment system of this application may include: The data acquisition module 410 is used to collect performance record data of aircraft maintenance personnel; the performance record data includes qualification and ability data, maintenance operation data, and performance evaluation data. The indicator assessment module 420 is used to assess the job competency indicators of aircraft maintenance personnel based on the performance record data. The job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills. The weight assignment module 430 is used to assign subjective weights to each job competency indicator using the analytic hierarchy process and objective weights to each job competency indicator using the entropy weight method. The weight fusion module 440 is used to linearly fuse subjective weights and objective weights to obtain the comprehensive weights of various job competency indicators. The competency assessment module 450 is used to comprehensively assess the job competency of aircraft maintenance personnel based on various job competency indicators and comprehensive weights through a machine learning model.

[0107] In one implementation, the qualification and competency data includes training and examination records, qualification and retraining records; the maintenance operation data includes maintenance records, electronic work cards, and fault handling records; and the assessment and evaluation data includes quality and safety reports, peer reviews, and error and violation records. The indicator evaluation module 420 may include: Assess the knowledge level of aircraft maintenance personnel based on training and examination records, qualification and retraining records, and troubleshooting records; and... The skill proficiency of aircraft maintenance personnel is assessed based on electronic work cards, maintenance records, fault handling records, and training and examination records; and, The work quality of aircraft maintenance personnel is assessed based on electronic work cards, maintenance records, quality and safety reports, error and violation records, and fault handling records; and... The behavioral habits of aircraft maintenance personnel are assessed based on error and violation records, quality and safety reports, electronic work cards, peer reviews, maintenance records, and fault handling records; and... The soft skills of aircraft maintenance personnel are assessed based on peer reviews, quality and safety reports, error and violation records, electronic work cards, maintenance records, and fault handling records.

[0108] In one implementation, the Analytic Hierarchy Process (AHP) is used to reflect job requirements and industry experience; when the weight assignment module 430 performs the step of assigning corresponding subjective weights to each job competency indicator using the AHP, it may include: The original judgment matrix construction submodule is used to compare the importance of each pair of job competency indicators using the 1-9 scale method of the analytic hierarchy process, in order to construct the original judgment matrix for pairwise comparisons at the criterion layer; the criterion layer consists of multiple job competency indicators. The column normalization submodule is used to normalize the original judgment matrix column by column to obtain a normalized matrix; The row calculation submodule is used to sum the normalized matrix row by row to obtain the row sum vector. The vector normalization submodule is used to normalize rows and vectors to obtain the subjective weights of various job competency indicators. The weight assignment module 430 may also include: The consistency verification submodule is used to perform consistency verification on the original judgment matrix based on the subjective weights of each job competency indicator. The validity determination submodule is used to determine the validity of the subjective weights of each job competency indicator when the original judgment matrix passes the consistency test.

[0109] In one embodiment, the aircraft maintenance personnel include multiple individuals; the entropy weight method is used to reflect the data distribution characteristics; when the weight assignment module 430 performs the step of assigning corresponding objective weights to each job competency indicator using the entropy weight method, it may include: The evaluation sample acquisition submodule is used to acquire evaluation samples for each aircraft maintenance worker; the evaluation samples include scores for various job competency indicators. The original data matrix construction submodule is used to construct the original data matrix using multiple evaluation samples; The indicator standardization processing submodule is used to standardize the original data matrix to obtain a standardized matrix; The indicator weight calculation submodule is used to calculate the indicator weight of each evaluation sample in the standardized matrix for each job competency indicator. The information entropy calculation submodule is used to calculate the information entropy of each job competency indicator based on the indicator weight. The difference coefficient calculation submodule is used to calculate the difference coefficient of various job competency indicators based on information entropy. The entropy weight calculation submodule is used to calculate the entropy weight of each job competency indicator based on the difference coefficient, thereby obtaining the objective weight of each job competency indicator.

[0110] In one embodiment, the weight fusion module 440 may include: The trust score acquisition submodule is used to acquire the first trust score of subjective weights and the second trust score of objective weights; the sum of the first trust score and the second trust score is 1, and the first trust score is less than the second trust score; The comprehensive weight calculation submodule is used to perform a weighted summation of the subjective weight, first degree of trust, objective weight, and second degree of trust of each job competency indicator to obtain the comprehensive weight of each job competency indicator.

[0111] In one embodiment, job competency is represented by a job competency score; the competency assessment module 450 may include: The evaluation sample acquisition submodule is used to acquire evaluation samples of aircraft maintenance personnel; the evaluation samples include knowledge level scores, skill proficiency scores, work quality scores, behavioral habits scores, and soft skills scores; The job competency score calculation submodule is used to calculate the job competency score of aircraft maintenance personnel by weighting and summing the knowledge level score, skill proficiency score, work quality score, behavioral habit score, soft skill score, and various comprehensive weights through a machine learning model.

[0112] In one embodiment, the machine learning model includes a clustering analysis algorithm and a prediction evaluation algorithm; the system may further include: The clustering analysis module is used to classify aircraft maintenance personnel based on their capabilities using clustering algorithms derived from machine learning models; and... The predictive assessment module is used to identify skill gaps and provide early warnings of safety risks for aircraft maintenance personnel by employing predictive assessment algorithms through machine learning models.

[0113] In one embodiment, the clustering analysis module may include: The first classification submodule is used to classify aircraft maintenance personnel into the first competency level using a machine learning model if the job competency score is greater than or equal to the first competency threshold; or... The second classification submodule is used to classify aircraft maintenance personnel into a second competency level using a machine learning model if the job competency score is less than the first competency threshold but greater than or equal to the second competency threshold; or... The third sub-module is used to classify aircraft maintenance personnel into the third competency level through a machine learning model if the job competency score is less than the second competency threshold but greater than or equal to the third competency threshold. Among them, the first competency threshold > the second competency threshold > the third competency threshold, and the first ability level > the second ability level > the third ability level.

[0114] In one embodiment, the prediction and evaluation module may include: The competency gap identification submodule is used to identify, through machine learning models, the competency indicators whose target indicator scores are lower than the set passing scores as competency gaps in the dimension of aircraft maintenance personnel; the target indicator score is the product of the score of a single competency indicator and its corresponding comprehensive weight. The risk intervention measures generation submodule is used to generate corresponding risk intervention measures for aircraft maintenance personnel based on their capability shortcomings in the relevant dimension. The risk intervention measures include at least one of the following: personalized training programs, job matching suggestions, and human resource allocation strategies.

[0115] As can be seen from this example, the solution provided in this application achieves comprehensive assessment by integrating multi-source performance record data (qualification and capability data, maintenance operation data, and performance evaluation data), dynamic assessment by a multi-dimensional job competency indicator system (knowledge level, skill proficiency, work quality, behavioral habits, and soft skills), objective assessment by combining subjective and objective assessments, real-time, standardized, and predictive assessment by machine learning models, intuitive assessment by visualizing competency profiles, and continuous assessment by a closed-loop management mechanism. This effectively improves the accuracy of assessments, the relevance of training, and the effectiveness of risk control, promoting the transformation of aviation maintenance human resource management towards data-driven intelligence and meeting the requirements of digital, refined, and intelligent management in civil aviation.

[0116] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0117] Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0118] See Figure 5 The electronic device 500 includes a memory 510 and a processor 520.

[0119] The processor 520 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. Memory 510 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by the processor 520 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 510 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 510 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0120] The memory 510 stores executable code, which, when processed by the processor 520, can cause the processor 520 to execute part or all of the methods described above.

[0121] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0122] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) that, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0123] This application also provides a computer program product, which includes computer instructions that, when executed by a processor, implement the method described above.

[0124] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for assessing the job competency of aircraft maintenance personnel, characterized in that, include: Collect performance record data of aircraft maintenance personnel; the performance record data includes qualification and competency data, maintenance operation data, and performance evaluation data; Based on the performance record data, the job competency indicators of the aircraft maintenance personnel are evaluated; the job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills. The Analytic Hierarchy Process (AHP) was used to assign subjective weights to each of the job competency indicators, and the entropy weight method was used to assign objective weights to each of the job competency indicators. The subjective weights and objective weights are linearly fused to obtain the comprehensive weights of each job competency indicator; The machine learning model is used to comprehensively evaluate the job competency of the aircraft maintenance personnel based on the aforementioned job competency indicators and their combined weights.

2. The method according to claim 1, characterized in that, The qualification and competency data includes training and examination records, qualification and retraining records; the maintenance operation data includes maintenance records, electronic work cards, and fault handling records; the assessment and evaluation data includes quality and safety reports, peer reviews, and error and violation records; the evaluation of the aircraft maintenance personnel's job competency indicators based on the performance record data includes: The knowledge level of the aircraft maintenance personnel is assessed based on the training and examination records, the qualification and retraining records, and the fault handling records; and... The skill proficiency of the aircraft maintenance personnel is assessed based on the electronic work card, the maintenance record, the fault handling record, and the training and examination record; and, The work quality of the aircraft maintenance personnel is evaluated based on the electronic work card, the maintenance record, the quality and safety report, the error and violation record, and the fault handling record; and... The behavioral habits of the aircraft maintenance personnel are assessed based on the error and violation records, the quality and safety reports, the electronic work cards, the peer reviews, the maintenance records, and the fault handling records; and... The soft skills of the aircraft maintenance personnel are assessed based on the peer reviews, the quality and safety reports, the error and violation records, the electronic work cards, the maintenance records, and the fault handling records.

3. The method according to claim 1, characterized in that, The Analytic Hierarchy Process (AHP) is used to reflect job requirements and industry experience; the AHP is used to assign corresponding subjective weights to each of the job competency indicators, including: The importance of each pair of job competency indicators is compared using the 1-9 scale method of the analytic hierarchy process to construct the original judgment matrix for pairwise comparisons of the criteria layer; the criteria layer consists of multiple job competency indicators. The original judgment matrix is ​​normalized column-wise to obtain a normalized matrix; The normalized matrix is ​​summed row by row to obtain a row sum vector; The rows and vectors are normalized to obtain the subjective weights of each of the job competency indicators. The method further includes: Based on the subjective weights of each of the job competency indicators, a consistency check is performed on the original judgment matrix. When the original judgment matrix passes the consistency test, the subjective weights of each of the job competency indicators are determined to be valid.

4. The method according to claim 1, characterized in that, The aircraft maintenance personnel include multiple individuals; the entropy weight method is used to reflect the data distribution characteristics; the entropy weight method is used to assign corresponding objective weights to each of the job competency indicators, including: Obtain evaluation samples for each of the aforementioned aircraft maintenance personnel; the evaluation samples include scores for each of the aforementioned job competency indicators; The original data matrix is ​​constructed using multiple evaluation samples. The original data matrix is ​​standardized to obtain a standardized matrix; Calculate the weight of each evaluation sample in each of the job competency indicators in the standardized matrix; Based on the weighting of the indicators, calculate the information entropy of each of the job competency indicators. Based on the information entropy, calculate the difference coefficient of each of the job competency indicators; Based on the difference coefficient, the entropy weight of each of the job competency indicators is calculated to obtain the objective weight of each of the job competency indicators.

5. The method according to claim 1, characterized in that, The process of linearly fusing the subjective weights and the objective weights to obtain the comprehensive weights for each of the job competency indicators includes: Obtain the first degree of trust for the subjective weight and the second degree of trust for the objective weight; the sum of the first degree of trust and the second degree of trust is 1, and the first degree of trust is less than the second degree of trust; The subjective weight, first degree of trust, objective weight, and second degree of trust of each job competency indicator are weighted and summed to obtain the comprehensive weight of each job competency indicator.

6. The method according to claim 1, characterized in that, The job competency is represented by a job competency score; the comprehensive evaluation of the aircraft maintenance personnel's job competency using a machine learning model based on each of the job competency indicators and their combined weights includes: Obtain an evaluation sample of the aircraft maintenance personnel; the evaluation sample includes knowledge level score, skill proficiency score, work quality score, behavioral habit score, and soft skills score; The machine learning model is used to perform a weighted summation of the knowledge level score, skill proficiency score, work quality score, behavioral habit score, soft skill score, and the comprehensive weight of each item to obtain the job competency score of the aircraft maintenance personnel.

7. The method according to claim 6, characterized in that, The machine learning model includes clustering analysis algorithms and prediction evaluation algorithms; the method further includes: The machine learning model employs the clustering analysis algorithm to classify the aircraft maintenance personnel according to their capabilities; and... The machine learning model employs the prediction and evaluation algorithm to identify skill gaps and provide early warnings of safety risks for aircraft maintenance personnel.

8. The method according to claim 7, characterized in that, The process of classifying the aircraft maintenance personnel's capabilities using the clustering analysis algorithm through the machine learning model includes: If the job competency score is greater than or equal to the first competency threshold, then the aircraft maintenance personnel are classified into the first competency level using the machine learning model; or, If the job competency score is less than the first competency threshold but greater than or equal to the second competency threshold, then the aircraft maintenance personnel are classified into the second competency level using the machine learning model; or, If the job competency score is less than the second competency threshold but greater than or equal to the third competency threshold, the aircraft maintenance personnel will be classified into the third competency level through the machine learning model. Wherein, the first competence threshold > the second competence threshold > the third competence threshold, and the first ability level > the second ability level > the third ability level.

9. The method according to claim 7, characterized in that, The process of identifying skill gaps and providing safety risk warnings for aircraft maintenance personnel using the machine learning model and the prediction and evaluation algorithm includes: The machine learning model identifies job competency indicators whose target scores are lower than the set passing scores as the competency weaknesses in the dimension of the aircraft maintenance personnel; the target score is the product of the score of a single job competency indicator and its corresponding comprehensive weight. Based on the shortcomings in the aforementioned dimension, corresponding risk intervention measures are generated for the aircraft maintenance personnel; the risk intervention measures include at least one of the following: personalized training programs, job matching suggestions, and human resource allocation strategies.

10. A competency assessment system for aircraft maintenance personnel, characterized in that, include: The data acquisition module is used to collect performance record data of aircraft maintenance personnel; the performance record data includes qualification and ability data, maintenance operation data, and performance evaluation data. The indicator evaluation module is used to evaluate the job competency indicators of the aircraft maintenance personnel based on the job performance record data; the job competency indicators include knowledge level, skill proficiency, work quality, behavioral habits, and soft skills; The weight assignment module is used to assign subjective weights to each of the job competency indicators using the analytic hierarchy process (AHP) and to assign objective weights to each of the job competency indicators using the entropy weight method. The weight fusion module is used to linearly fuse the subjective weights and the objective weights to obtain the comprehensive weights of each of the job competency indicators; The competency assessment module is used to comprehensively assess the job competency of the aircraft maintenance personnel based on the various job competency indicators and their comprehensive weights using a machine learning model.

Images