A method and system for evaluating the ability of an operator based on individual difference theory

Abstract

The application belongs to the field of nuclear power plant operator training, and provides an operator ability evaluation method and system based on individual difference theory. The method comprises the following steps: obtaining deviation facts and automatically perfecting evaluation based on five elements; performing ability dimension classification and scoring to generate basic function ability graph; performing root cause analysis, combining individual difference theory and group and individual data, calculating ability characteristic dimension evaluation results, and generating ability characteristic dimension graph; and recommending improvement measures according to the two types of graphs and root causes. The application converts scattered deviation facts into standardized and visualized ability evaluation results, identifies weak items from the aspects of basic skills and individual ability characteristics, improves the objectivity of evaluation and the pertinence of improvement measures, and realizes the explicitness of operator ability, the standardization of evaluation, and the closed-loop management of improvement.

Description

Technical Field

[0001] This application pertains to the field of nuclear power plant operator training and relates to a method and system for evaluating operator competence based on the theory of individual differences. Background Technology

[0002] Nuclear power plant operators are core personnel responsible for the operation control, anomaly handling, and nuclear safety assurance of nuclear power plants. Their professional competence, operational standardization, risk identification capabilities, and judgment and handling abilities under abnormal conditions directly affect the safe, stable, and reliable operation of the nuclear power unit. During nuclear power plant operation, operators need to have a comprehensive understanding of the nuclear power plant system equipment, operating procedures, technical specifications, human factors tools, and various operational management requirements. They must be able to accurately identify changes in the unit's status during normal operation, transient processes, equipment degradation, abnormal conditions, and accident conditions, and promptly take operational measures that comply with procedures and safety principles, thereby reducing the risk of escalation of faults, equipment damage, and operational events. Therefore, providing systematic training, competency assessment, and continuous improvement for operators is an important component of the intrinsic safety management of nuclear power plant personnel.

[0003] Current nuclear power plant operator training and evaluation typically rely on job skills training, theoretical knowledge assessments, simulator drills, and operational performance feedback. While these methods can reflect operators' mastery of knowledge, procedures, and operational skills to some extent and provide a basis for training plan development and job authorization management, in practice, existing evaluation methods focus more on operators' performance in a specific task, skill, or training phase. They lack further exploration of the underlying competency dimensions, root causes, and individual ability characteristics behind operators' deviations, failing to reveal the deeper internal factors contributing to operator competency deficiencies.

[0004] During training or routine work observations, instructors and observers typically record deviations made by operators and use this information for subsequent evaluation and correction. However, because the recording of deviations relies on the observers' experience and writing skills, different observers may differ in the completeness of their descriptions of the same deviation, their focus, and their evaluation criteria. For example, some records only describe the operational result, lacking crucial information such as the unit's status, task context, responsible position, specific operational process, error point, and potential risk consequences. This makes it difficult to accurately classify capabilities, analyze root causes, and implement targeted improvements. Furthermore, the recording, review, classification, and scoring of deviations usually require manual work, resulting in a large workload, low evaluation efficiency, and difficulty in maintaining consistent evaluation criteria.

[0005] Furthermore, existing operator competency assessments are mostly based on single observations or periodic evaluations, lacking continuous summarization, statistical analysis, and graphical representation of multiple deviations. Existing methods often struggle to quantify operators' capabilities across fundamental functional dimensions such as monitoring, control, conservatism, teamwork, knowledge, and behavioral norms using a unified model, and also fail to intuitively identify operators' strengths and weaknesses across different competency dimensions. Even when a weakness is identified in an operator, existing methods typically stop at assigning learning, repetitive training, or general reminders, lacking a mechanism for correlating deviations, competency dimensions, root causes, and improvement measures, resulting in insufficient precision and effectiveness of improvement measures.

[0006] Meanwhile, operator inadequacies do not solely stem from knowledge or skill deficiencies; they may also be related to relatively stable individual abilities such as execution, communication, judgment, learning ability, responsibility, and physical stamina. Different operators exhibit individual differences in psychological characteristics, behavioral habits, learning styles, communication patterns, sense of responsibility, and physical condition. These differences influence their performance in complex working conditions, stressful environments, and team-based tasks. Existing training and evaluation systems do not adequately address these individual differences, making it difficult to effectively link operators' external behavioral deviations with their internal competencies, and also hindering comparative analysis of operator capabilities using both group and individual data.

[0007] With the development of artificial intelligence and big data analytics, the use of AI models for automatic completion, integrity assessment, competency dimension classification, and scoring of text-based deviation facts has reached a certain technological foundation. By constructing standardized deviation fact training and validation libraries, AI models can learn the standard descriptive structure of deviation facts, competency dimension classification rules, and scoring standards, thereby assisting observers in improving record quality and evaluation efficiency. However, how to organically combine automatic deviation fact completion, automatic competency dimension classification and scoring, root cause analysis, individual difference theory, competency map generation, and improvement measure recommendations to form a systematic competency evaluation and improvement scheme applicable to nuclear power plant operators remains a problem that needs to be solved in the current technology.

[0008] Therefore, there is an urgent need to provide a method and system for evaluating operator capabilities based on the theory of individual differences. This system should be able to standardize, improve, and evaluate deviations that occur during training or work, automatically identify the basic functional competence dimensions corresponding to the deviations and assign scores, and further combine root cause analysis, group data, and individual data to calculate the evaluation results of operators on multiple competence characteristic dimensions. This will generate basic functional competence maps and competence characteristic dimension maps, and recommend targeted improvement measures based on competence weaknesses and root causes. This will enable the explicit identification of operator competence status, the standardization of the evaluation process, and the closed-loop management of competence improvement. Summary of the Invention

[0009] The purpose of this application is to design a method and system for evaluating operator capabilities based on the theory of individual differences. This method classifies and summarizes various deviations of operators, develops a technical capability map of operators by using scores from instructors and observers, and conducts root cause analysis of deviations. Based on the theory of individual differences, a set of capability characteristic maps is developed. By using the basic functional capability map and capability characteristic map, the capabilities of operators can be made explicit, which can be used for targeted improvement of personnel capabilities and scientific allocation of on-site work and risk warning.

[0010] Technical solution to achieve the purpose of this application: This application provides a method for evaluating operator competence based on the theory of individual differences, including: S1, Obtain facts of deviations by operators during training or work, wherein the facts of deviations include the five elements of deviation facts; S2, based on the five elements of deviation facts, automatically improves and evaluates the deviation facts, and generates improved deviation facts, fact completeness scores and scoring basis; S3, classify and score the improved deviation facts according to the ability dimensions to obtain the basic functional ability dimensions and scoring results corresponding to the deviation facts; S4. Based on the basic functional competence dimensions and the scoring results, calculate the operator's competence scores on multiple basic functional competence dimensions and generate an operator basic functional competence map. S5, perform root cause analysis on the aforementioned deviation facts to obtain the root cause classification results; S6. Based on the root cause classification results and the individual difference theory, and combining group data and individual data, calculate the evaluation results of the operator on multiple capability characteristic dimensions. S7. Based on the evaluation results on the capability characteristic dimensions, generate an operator capability characteristic dimension map; S8. Based on the basic functional capability map, the capability feature dimension map, and the root cause classification results, recommend measures to improve operator capabilities.

[0011] Optionally, the five elements of the deviation fact include background, person, operation, error point, and risk and consequences; wherein, the background is used to characterize the unit status, task execution or abnormal operating condition, the person is used to characterize the person responsible for the behavior and their position, the operation is used to characterize the specific behavior of the person responsible and the tools or documents used, the error point is used to characterize the core deviation of the behavior that does not meet the job expectations or ability requirements, and the risk and consequences are used to characterize the risks or consequences that the error point may cause or has already caused.

[0012] Optionally, step S2, which involves automatically improving and evaluating the deviation facts to generate improved deviation facts, factual completeness scores, and scoring criteria, includes: Build training and validation libraries for automatic fact-finding and evaluation of biases; The training library includes standardized deviation fact samples that meet the five elements of deviation facts, and the verification library includes deviation fact samples with missing, incorrect or incomplete content and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, so that the artificial intelligence model has the ability to complete biased facts, score fact integrity, and output scoring basis. The artificial intelligence model identifies the five missing or incomplete elements in the original deviation facts and outputs an evaluation result that includes a complete description of the deviation facts, a completeness score, and the basis for the score.

[0013] Optionally, in step S3, the basic functional dimensions include six primary dimensions: monitoring, control, conservatism, teamwork, knowledge, and behavioral norms.

[0014] Optionally, each of the basic functional dimensions may contain multiple secondary dimensions.

[0015] Optionally, in step S3, the scoring results are categorized according to the severity of the deviation facts into good facts, expected facts, minor deviations, moderate deviations, and severe deviations. The first scoring interval corresponds to good facts, the second scoring interval corresponds to meeting expectations, the third scoring interval corresponds to minor deviations, the fourth scoring interval corresponds to moderate deviations, and the fifth scoring interval corresponds to serious deviations.

[0016] Optionally, the scoring result adopts a full score of 5 points, where: The rating range for good facts is [4.5, 5]. The expected score range is [4, 4.5); The scoring range for slight deviations is [3.5, 4); The scoring range for general deviation is [3, 3.5); The scoring range for severe deviation is [0, 3).

[0017] Optionally, step S3 includes: Construct training and validation libraries for ability dimension classification and scoring; The training library includes standardized bias fact samples with labeled basic functional dimensions and scoring results, and the validation library includes bias fact samples with classification or scoring bias and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, enabling the artificial intelligence model to automatically classify and score biased facts based on their capability dimensions.

[0018] Optionally, step S4 includes: Statistically analyze the target operator's multiple ratings within a preset time period according to the basic functional competence dimension; The ability score for the same basic functional competency dimension is obtained by averaging multiple ratings. The calculation formula is as follows: Where I represents the corresponding basic functional dimension, S I This represents the basic functional ability score for a certain dimension, where i represents the score number and s represents the score. i This represents the i-th rating result in the corresponding basic functional competence dimension, where n is the number of rating results in the corresponding basic functional competence dimension. A radar chart is generated based on the capability scores of multiple basic functional dimensions, serving as the basic functional capability map of the operator.

[0019] Optionally, step S5 includes guiding observers and / or operators to perform analysis according to a preset root cause analysis process based on the confirmed deviation facts; and storing the root cause classification results in a database.

[0020] Optionally, in step S6, the capability characteristics dimensions include execution ability, communication ability, judgment ability, learning ability, responsibility ability, and physical ability.

[0021] Optionally, step S6 includes: Map the root cause classification results to the corresponding capability feature dimensions; The proportion of facts about weaknesses in each dimension of the statistical group to the total number of facts about the group (S) n ; The proportion of facts about the weaknesses of the target manipulator in each dimension of their competency characteristics to the total number of facts about the target manipulator (T) n ; The percentage of facts in the statistical group that deviate below expectations across all dimensions of ability characteristics, F. n ; The percentage of instances where the target manipulator's performance deviated below expectations across all capability characteristic dimensions out of the total number of instances involving that individual. n ; According to S n T n F n and f nCalculate the evaluation results P of the target operator on each dimension of capability characteristics. n The calculation formula is: Where 2 is the correction factor.

[0022] Optionally, step S7 includes: evaluating the results P from multiple capability feature dimensions. n A radar chart is generated as a dimension map of the operator's capability characteristics.

[0023] Optionally, step S8 includes: Identify the fundamental functional weaknesses in the fundamental functional capability map; Identify the capability feature weaknesses in the capability feature dimension map; Based on the basic functional weakness, the capability characteristic weakness, and the root cause classification result, at least one capability improvement measure is matched from the preset improvement measure library.

[0024] Optionally, step S8 may be followed by: Obtain improvement evaluation data after the operator implements the capability improvement measures; Update the operator's deviation fact data, basic functional strength map, and capability characteristic dimension map based on the improved evaluation data; Determine whether the improvement results have achieved the preset improvement goals. If not, recommend or adjust the capability improvement measures to form a closed loop of capability evaluation and improvement.

[0025] An operator competence evaluation system based on individual differences theory includes: The deviation fact acquisition module is used to acquire deviation facts of operators during training or work, and the deviation facts include the five elements of deviation facts; The deviation fact improvement and evaluation module is used to automatically improve and evaluate the deviation fact based on the five elements of the deviation fact, and generate the improved deviation fact, fact completeness score and scoring basis; The capability dimension classification and scoring module is used to classify and score the improved deviation facts according to capability dimensions, and obtain the basic functional capability dimensions and scoring results corresponding to the deviation facts. The basic functional competence map generation module is used to calculate the operator's ability score on multiple basic functional competence dimensions based on the basic functional competence dimensions and the scoring results, and generate the operator's basic functional competence map. The root cause analysis module is used to perform root cause analysis on the deviation facts and obtain the root cause classification results; The competency characteristic evaluation module is used to calculate the evaluation results of operators on multiple competency characteristic dimensions based on the root cause classification results and individual difference theory, combined with group data and individual data. The capability feature map generation module is used to generate an operator capability feature dimension map based on the evaluation results on the capability feature dimensions. The improvement measure recommendation module is used to recommend operator capability improvement measures based on the basic functional capability map, the capability feature dimension map, and the root cause classification results.

[0026] Optionally, the five elements of the deviation fact include background, people, operation, point of error, and risk and consequences; The background is used to characterize the unit status, task execution, or abnormal operating conditions; the person is used to characterize the person responsible for the action and their position; the operation is used to characterize the specific behavior of the person responsible and the tools or documents used; the error point is used to characterize the core deviation of the behavior from the job expectations or ability requirements; and the risk and consequence are used to characterize the risk or consequence that the error point may cause or has already caused.

[0027] Optionally, the deviation fact-perfecting assessment module includes: The first training library construction unit is used to construct a training library for automatic improvement and evaluation of biased facts. The training library includes standardized biased fact samples that meet the requirements of the five elements of biased facts. The first verification library construction unit is used to construct a verification library for automatic improvement and evaluation of deviation facts. The verification library includes deviation fact samples with missing, incorrect or incomplete content and corresponding evaluation results. The first model training and verification unit is used to train an artificial intelligence model using the training library and to verify and correct the artificial intelligence model using the verification library, so that the artificial intelligence model has the ability to complete biased facts, score fact integrity, and output scoring basis. The deviation fact output unit is used to identify the five missing or incomplete elements in the original deviation fact by the artificial intelligence model, and output the evaluation result including the improved deviation fact description, completeness score and scoring basis.

[0028] Optionally, the basic functional competence dimensions used in the competence dimension classification and scoring module include six primary dimensions: monitoring, control, conservatism, teamwork, knowledge, and behavioral norms.

[0029] Optionally, each of the basic functional dimensions may contain multiple secondary dimensions.

[0030] Optionally, the capability dimension classification and scoring module is used to classify the scoring results into good facts, expected facts, minor deviations, moderate deviations, and severe deviations according to the severity of the deviation facts; The first scoring interval corresponds to good facts, the second scoring interval corresponds to meeting expectations, the third scoring interval corresponds to minor deviations, the fourth scoring interval corresponds to moderate deviations, and the fifth scoring interval corresponds to serious deviations.

[0031] Optionally, the scoring result adopts a full score of 5 points, where: The rating range for good facts is [4.5, 5]. The expected score range is [4, 4.5); The scoring range for slight deviations is [3.5, 4); The scoring range for general deviation is [3, 3.5); The scoring range for severe deviation is [0, 3).

[0032] Optionally, the capability dimension classification and scoring module includes: The second training library construction unit is used to construct a training library for ability dimension classification and scoring. The training library includes normalized bias fact samples with labeled basic functional ability dimensions and scoring results. The second verification library construction unit is used to construct a verification library for ability dimension classification and scoring. The verification library includes bias fact samples with classification or scoring bias and corresponding evaluation results. The second model training and verification unit is used to train the artificial intelligence model using the training library and to verify and correct the artificial intelligence model using the verification library, so that the artificial intelligence model can automatically classify and score the biased facts according to the capability dimension.

[0033] Optionally, the basic functional competence map generation module is used to statistically analyze multiple rating results of the target operator within a preset time period according to the basic functional competence dimensions, and to calculate the average of multiple rating results under the same basic functional competence dimension to obtain the competence score for that basic functional competence dimension. The calculation formula is as follows: Where I represents the corresponding basic functional dimension, S I This represents the basic functional ability score for a certain dimension, where i represents the score number and s represents the score. i This represents the i-th rating result in the corresponding basic functional competence dimension, where n is the number of rating results in the corresponding basic functional competence dimension. The basic functional competence map generation module is also used to generate a radar map based on the capability scores of multiple basic functional competence dimensions, which serves as the operator's basic functional competence map.

[0034] Optionally, the root cause analysis module is used to guide observers and / or operators to perform analysis according to a preset root cause analysis process based on confirmed deviation facts, and to store the root cause classification results in a database.

[0035] Optionally, the capability characteristic dimensions adopted by the capability characteristic evaluation module include execution ability, communication ability, judgment ability, learning ability, responsibility ability, and physical ability.

[0036] Optionally, the capability characteristic evaluation module is used for: Map the root cause classification results to the corresponding capability feature dimensions; The proportion of facts about weaknesses in each dimension of the statistical group to the total number of facts about the group (S) n ; The proportion of facts about the weaknesses of the target manipulator in each dimension of their competency characteristics to the total number of facts about the target manipulator (T) n ; The percentage of facts in the statistical group that deviate below expectations across all dimensions of ability characteristics, F. n ; The percentage of instances where the target manipulator's performance deviated below expectations across all capability characteristic dimensions out of the total number of instances involving that individual. n ; According to S n T n F n and f n Calculate the evaluation results P of the target operator on each dimension of capability characteristics. n The calculation formula is: Where 2 is the correction factor.

[0037] Optionally, the capability feature map generation module is used to generate evaluation results P from multiple capability feature dimensions. n A radar chart is generated as a dimension map of the operator's capability characteristics.

[0038] Optionally, the improvement recommendation module is used for: Identify the fundamental functional weaknesses in the fundamental functional capability map; Identify the capability feature weaknesses in the capability feature dimension map; Based on the basic functional weakness, the capability characteristic weakness, and the root cause classification result, at least one capability improvement measure is matched from the preset improvement measure library.

[0039] Optionally, the system further includes an improved closed-loop management module, which is used for: Obtain improvement evaluation data after the operator implements the capability improvement measures; Update the operator's deviation fact data, basic functional strength map, and capability characteristic dimension map based on the improved evaluation data; Determine whether the improvement results have achieved the preset improvement goals. If not, recommend or adjust the capability improvement measures to form a closed loop of capability evaluation and improvement.

[0040] Optionally, the system further includes a data storage module, which stores deviation fact data, improved deviation facts, fact integrity scores, scoring basis, basic functional capability dimensions, scoring results, root cause classification results, capability characteristic dimension evaluation results, basic functional capability maps, capability characteristic dimension maps, and capability improvement measure data.

[0041] Optionally, the system further includes a data display module, which is used to display the basic functional capability map and the capability characteristic dimension map according to the operator, and to display relevant evaluation data in the process of operator capability improvement.

[0042] The beneficial technical effects of this application are as follows: This application acquires deviation facts of operators during training or work, and automatically improves and evaluates these deviation facts based on the five elements of deviation facts. It further classifies and scores the improved deviation facts according to basic functional competence dimensions, generating a basic functional competence map of the operators. Simultaneously, it performs root cause analysis on the deviation facts and calculates the evaluation results of operators on multiple competence characteristic dimensions by combining individual difference theory, group data, and individual data, generating a competence characteristic dimension map of operators. Based on the basic functional competence map, competence characteristic dimension map, and root cause classification results, it recommends competence improvement measures. Therefore, this invention can transform the dispersed and unstructured deviation facts of operators into evaluable, quantifiable, and visualized competence evaluation results. This improves the standardization and processing efficiency of deviation fact recording, improvement, classification, scoring, and root cause analysis, and enables comprehensive identification of operator competence status from both basic functional competence and individual competence characteristic levels. This makes operator competence weaknesses and their causes more intuitive and clear, thereby improving the objectivity, pertinence, and accuracy of competence evaluation and improvement measure recommendations. This facilitates refined management of operator training improvement, job matching, and risk warning. Detailed Implementation

[0043] To enable those skilled in the art to better understand this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the embodiments described below are only a part of the embodiments of this application, and not all of them. Based on the embodiments described in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] This application relates to a method and system for evaluating operator competence based on the theory of individual differences. The method includes the following steps: S1, obtain facts about deviations of operators during training or work.

[0045] In this step, observers, instructors, or other personnel with evaluation authority observe the behavior of operators during training, simulator drills, operational shifts, emergency response drills, or daily work. When operators are found to be behaving in ways that do not meet job expectations, procedural requirements, management requirements, or competency standards, the corresponding deviation is recorded.

[0046] The deviation facts comprise five elements: background, personnel, operation, point of failure, and risk and consequences. Background characterizes the unit's status, task being performed, or abnormal operating condition; personnel characterize the person responsible for the action and their position; operation characterizes the specific actions of the responsible person and the tools or documents used; point of failure characterizes the core deviation where the action does not meet the job expectations or competency requirements; and risk and consequences characterize the risks or consequences that the point of failure may cause or have already caused.

[0047] For example, during a simulator exercise, the unit was in the power-up phase. The secondary loop operator activated the steam generator blowdown system according to the operating procedure. However, during the establishment of the blowdown flow, the operator opened the blowdown valve too quickly, causing the blowdown temperature to rise rapidly and triggering the blowdown system's protective isolation. In this deviation, "the unit was in the power-up phase" is the background, "the secondary loop operator" is the person, "activating the steam generator blowdown system and opening the blowdown valve according to the operating procedure" is the operation, "opening the blowdown valve too quickly" is the error, and "causing the blowdown temperature to rise too high and triggering the blowdown system's protective isolation" is the risk and consequence.

[0048] Table 1. Detailed description of each element S2, based on the five elements of deviation facts, automatically improves and evaluates the deviation facts, and generates improved deviation facts, factual completeness scores and scoring basis.

[0049] In this step, the deviation fact improvement assessment module in the system calls an artificial intelligence model to identify the original deviation facts input by the observer and determine whether there are problems such as missing background, unclear characters, insufficient description of the operation process, unclear error points, missing or incomplete expression of risks and consequences.

[0050] To achieve the above functions, a training library and a validation library are pre-built for the automatic completion and evaluation of biased facts before the artificial intelligence model is put into use. The training library includes standardized biased fact samples that meet the five elements of biased facts, while the validation library includes biased fact samples with missing, incorrect, or incomplete content and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, enabling the artificial intelligence model to have the ability to complete biased facts, score fact completeness, and output scoring criteria.

[0051] After training, the AI ​​model can identify and supplement missing information in the original deviation facts, and output a more complete description of the deviation facts, a completeness score, and the basis for the score. For example, for the original record "When the operator established the steam generator blowdown flow rate, the blowdown valve opened too quickly, causing the blowdown system to be isolated," the AI ​​model can supplement the description with unit operating conditions, personnel, operating documents, operating procedures, quantitative error points, and consequences, forming a more complete description of the deviation facts, and providing a corresponding score and the basis for the score.

[0052] After the AI ​​model outputs the improved deviation facts, observers verify each item of the supplementary content. If the supplementary content from the AI ​​model matches the actual observations, the improved deviation fact is confirmed; if there are inaccuracies, the observers modify it or return it for further improvement. The confirmed deviation facts are stored in the database for subsequent capability classification, scoring, root cause analysis, and model training.

[0053] Table 2. Examples of Deviation Fact Assessment S3. Classify and score the improved deviation facts according to the capability dimensions to obtain the basic functional capability dimensions and scoring results corresponding to the deviation facts.

[0054] In this step, the capability dimension classification and scoring module classifies the deviation facts according to the improved deviation facts into basic functional capability dimensions and scores them according to the severity of the deviation facts. The basic functional capability dimensions include six primary dimensions: monitoring, control, conservatism, teamwork, knowledge, and behavioral norms. Each primary dimension can further include multiple secondary dimensions.

[0055] The monitoring dimension can include the following secondary dimensions: comprehensive monitoring of unit status during shift handover, regular inspection of unit parameters, sensitivity to alarms and abnormal trends, increased monitoring intensity after equipment degradation, increased monitoring intensity of key parameters after transient events, and enhanced long-term monitoring of key parameters after accidents. The control dimension can include defining control objectives, maintaining equipment in the required state after automatic actions fail, analyzing operational risks and checking that equipment actions are consistent with expectations, and achieving seamless manual / automatic switching. The conservative dimension can include analyzing the impact and developing measures after equipment failure or degradation, quickly placing the unit in a safe state after transient events, consulting technical specifications after equipment status changes, maintaining margins in parameter control, accurate and verified reactive calculations, and ensuring team decision-making and monitoring for important operations. The team dimension can include timely notification of important information to the team, complete notification of work tasks and risk information to the team, ensuring that job responsibilities are assigned when personnel leave, and thorough internal team discussions on risks and decisions. The knowledge dimension can include understanding the system's equipment-related control logic, understanding equipment operating requirements and degradation risks, correctly understanding procedures and technical specifications, understanding management requirements, and familiarity with the human-machine interface. The behavioral norms dimension can include secondary dimensions such as performing regular inventory checks and alarm responses as required by management, being proficient in using tools to prevent human error, and communicating fluently and clearly.

[0056] Table 3. Examples of Secondary Dimensions The scoring results are categorized according to the severity of the deviation: good facts, meeting expectations, minor deviation, moderate deviation, and serious deviation. A maximum score of 5 points can be used, with the scoring range for good facts being [4.5, 5], for meeting expectations [4, 4.5), for minor deviation [3.5, 4), for moderate deviation [3, 3.5), and for serious deviation [0, 3].

[0057] Table 4. Examples of Scoring Criteria In one implementation, ability dimension classification and scoring can be performed manually by an observer. In another implementation, ability dimension classification and scoring can be automatically performed by an artificial intelligence model, and then reviewed and confirmed by an observer. To achieve automatic classification and scoring by artificial intelligence, a training library and a validation library are pre-built for ability dimension classification and scoring. The training library includes normalized biased fact samples labeled with basic functional ability dimensions and scoring results, while the validation library includes biased fact samples with classification or scoring biases and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, enabling the artificial intelligence model to automatically classify and score biased facts in terms of ability dimensions.

[0058] S4. Based on the basic functional competence dimensions and scoring results, calculate the operator's competence scores on multiple basic functional competence dimensions and generate an operator basic functional competence map.

[0059] In this step, the basic functional competence mapping module statistically analyzes multiple ratings of the target operator within a preset time period, according to the basic functional competence dimensions. The preset time period can be a training cycle, an authorization cycle, a month, a quarter, a year, or other time ranges set according to management needs.

[0060] For multiple ratings within the same basic functional competency dimension, calculate their average to obtain the competency score for that dimension. The calculation formula is as follows: Where I represents the corresponding basic functional dimension, S I This represents the basic functional ability score for a certain dimension, where i represents the score number and s represents the score. i This represents the i-th rating result of the corresponding basic functional ability dimension, where n is the number of rating results for the corresponding basic functional ability dimension.

[0061] After calculating the competency scores for the six basic functional competency dimensions—monitoring, control, conservatism, teamwork, knowledge, and behavioral norms—a radar chart is generated as the operator's basic functional competency map. This map visually displays the operator's strengths and weaknesses across different basic functional competency dimensions, providing a basis for subsequent root cause analysis, competency improvement, and job matching.

[0062] For example, if an operator generates multiple deviations within a preset period, with scores of 3.5, 4.0, and 3.8 for the "surveillance" dimension and 3.0, 3.2, and 3.4 for the "control" dimension, the system calculates the corresponding averages and plots the scores for the six basic competency dimensions as a radar chart. If the control dimension score is significantly lower than the other dimensions, then the control dimension is identified as one of the operator's weaknesses in basic competency.

[0063] S5, perform a root cause analysis on the aforementioned deviation facts to obtain the root cause classification results.

[0064] In this step, the root cause analysis module guides observers and / or operators to conduct analysis according to a pre-defined root cause analysis process based on confirmed deviation facts. This analysis process can be presented in the form of questions and answers, options, hierarchical judgments, or a process tree, allowing operators and observers to gradually locate the root cause of the deviation facts through multiple simple selections.

[0065] Root cause analysis can be conducted from aspects such as personnel factors, task factors, communication factors, knowledge and skills factors, physical condition factors, attention factors, sense of responsibility factors, and external interference factors. For example, for situations where operational deviations are caused by not hearing instructions clearly, the root cause can be classified as communication-related; for situations where judgment errors are caused by forgetting learned knowledge points, the root cause can be classified as learning-related; and for situations where poor physical condition leads to decreased operational attention, the root cause can be classified as physical-related.

[0066] After the root cause analysis is completed, the system stores the root cause classification results in the database for analysis of individual ability characteristics, monitoring of human factors performance, and recommendation of subsequent improvement measures.

[0067] S6. Based on the root cause classification results and the theory of individual differences, and combining group data and individual data, calculate the evaluation results of the operators on multiple capability characteristic dimensions.

[0068] In this step, the competency assessment module maps the root cause classification results to the corresponding competency dimensions. These competency dimensions include execution ability, communication ability, judgment ability, learning ability, responsibility ability, and physical ability.

[0069] Among them, execution ability is used to characterize the operator's ability to implement procedures, perform tasks, meet requirements, and maintain standardized behavior; communication ability is used to characterize the operator's ability to receive instructions, transmit information, communicate with the team, and confirm collaboration; judgment ability is used to characterize the operator's ability to judge the status of the unit, changes in risks, abnormal trends, and handling strategies; learning ability is used to characterize the operator's ability to understand, master, transfer, and retain knowledge and skills; responsibility ability is used to characterize the operator's ability to fulfill job responsibilities, proactively identify risks, strictly comply with requirements, and maintain safety awareness; physical ability is used to characterize the operator's ability related to physical condition, fatigue level, attention maintenance, and continuous work capacity.

[0070] When calculating the evaluation results for each ability characteristic dimension, the system uses both group data and individual data. Specifically, it calculates the proportion S of the number of weaknesses in each ability characteristic dimension of the group to the total number of facts in the group. n The proportion of facts about the weaknesses of the target manipulator in each dimension of their competency characteristics to the total number of facts about the target manipulator (T). n The percentage of facts in the statistical group that deviate below expectations across all capability characteristic dimensions (F) out of the total number of facts. n The percentage of instances where the statistical target manipulator's performance deviated below expectations across all capability characteristic dimensions out of the total number of instances involving that individual. n According to S n T n Fn and f n Calculate the evaluation results P of the target operator on each dimension of capability characteristics. n .

[0071] In one implementation, the system can calculate the evaluation result P of the target operator on the capability characteristic dimension according to the following formula. n : Where 2 is the correction factor.

[0072] The above calculation method allows for a comparison of the target operator's performance on a specific capability dimension with the group average. If the percentage of weaknesses and the percentage of below-expectations in a specific capability dimension are significantly higher than the group average, the evaluation result for that capability dimension is low, indicating that the operator may have a relatively prominent weakness in that capability dimension.

[0073] S7. Based on the evaluation results on the capability characteristic dimension, generate an operator capability characteristic dimension map.

[0074] In this step, the competency profile generation module generates a radar chart from the evaluation results Pn of six competency profile dimensions: execution, communication, judgment, learning, responsibility, and physical ability. This chart serves as the operator's competency profile dimension map. This map is used to display the operator's individual competency profile status relative to the group level.

[0075] For example, if an operator's judgment score is significantly lower than their scores in execution, communication, learning, responsibility, and physical abilities, the system will identify judgment as a weakness in their competency profile. Managers can then further examine the facts, root causes, scenarios, and historical trends related to the judgment deficit to determine if specific intervention is needed.

[0076] S8. Based on the basic functional capability map, the capability feature dimension map, and the root cause classification results, recommend measures to improve operator capabilities.

[0077] In this step, the improvement measure recommendation module first identifies the basic functional weaknesses in the basic functional capability map, then identifies the capability feature weaknesses in the capability feature dimension map, and combines the root cause classification results to match at least one capability improvement measure in the preset improvement measure library.

[0078] The capacity-building measures can include knowledge learning, skills practice, psychological counseling, and physical training. Knowledge learning can include measures such as summary reports, learning assessments, and public speaking; skills practice can include measures such as sand table exercises, individual training, team training, and comprehensive evaluation; psychological counseling can include measures such as EAP (Employee Assistance Program), management interviews, and team building; and physical training can include measures such as individual exercise and team sports.

[0079] In one implementation, the improvement measure recommendation module makes recommendations based on the combination of basic functional weaknesses and capability weaknesses. For example, when the basic functional weakness is "control" and the capability weakness is "execution," sand table simulations, individual training, team training, or comprehensive assessments can be prioritized; when the basic functional weakness is "teamwork" and the capability weakness is "communication," public speaking, team building, or communication training can be prioritized; when the capability weakness is "responsibility," EAP, management interviews, or measures to strengthen responsibility awareness can be recommended based on root causes; and when the capability weakness is "physical fitness," individual exercise, team sports, or fatigue management-related measures can be recommended based on the actual situation.

[0080] Table 5. Examples of Recommended Improvement Measures After recommending capability improvement measures, the system can also form a capability evaluation and improvement closed loop. Specifically, it acquires improvement evaluation data after operators implement capability improvement measures, updates the operators' deviation fact data, basic functional capability map, and capability characteristic dimension map based on the improvement evaluation data; it determines whether the improvement results have achieved the preset improvement goals. If they have, the improvement completion result is recorded; if not, capability improvement measures are re-recommended or adjusted, thus forming a closed-loop management of capability evaluation, root cause analysis, measure recommendation, improvement implementation, effect tracking, and re-evaluation.

[0081] This embodiment also provides an operator competence evaluation system based on the theory of individual differences. The system includes a deviation fact acquisition module, a deviation fact improvement assessment module, a competence dimension classification and scoring module, a basic function capability map generation module, a root cause analysis module, a competence characteristic evaluation module, a competence characteristic map generation module, and an improvement measure recommendation module.

[0082] The Deviation Fact Acquisition Module acquires deviation facts observed by operators during training or work, including the five elements of a deviation fact. The Deviation Fact Improvement and Evaluation Module automatically improves and evaluates deviation facts based on the five elements, generating improved deviation facts, fact completeness scores, and scoring criteria. The Competency Dimension Classification and Scoring Module classifies and scores the improved deviation facts according to competency dimensions, obtaining the corresponding basic functional competency dimensions and scores. The Basic Functional Competency Map Generation Module calculates the operator's competency scores across multiple basic functional competency dimensions based on the basic functional competency dimensions and scoring results, generating a basic functional competency map for the operator. The Root Cause Analysis Module performs root cause analysis on the deviation facts, obtaining root cause classification results. The Competency Feature Evaluation Module calculates the operator's evaluation results across multiple competency feature dimensions based on the root cause classification results and individual difference theory, combining group and individual data. The Competency Feature Map Generation Module generates a competency feature dimension map for the operator based on the evaluation results across the competency feature dimensions. The Improvement Measures Recommendation Module recommends competency improvement measures for the operator based on the basic functional competency map, competency feature dimension map, and root cause classification results.

[0083] In one optional embodiment, the system further includes an improvement closed-loop management module, a data storage module, and a data display module. The improvement closed-loop management module acquires improvement evaluation data after operators implement capability improvement measures, updates the operators' deviation fact data, basic functional competence map, and capability characteristic dimension map based on the improvement evaluation data, and determines whether the improvement results meet the preset improvement goals. The data storage module stores deviation fact data, improved deviation facts, factual completeness scores, scoring criteria, basic functional competence dimensions, scoring results, root cause classification results, capability characteristic dimension evaluation results, basic functional competence map, capability characteristic dimension map, and capability improvement measure data. The data display module displays the basic functional competence map and capability characteristic dimension map according to the operators, and displays relevant evaluation data during the operator capability improvement process.

[0084] In practical applications, after observers identify deviant behavior during training or daily work, they input the original deviant facts via a terminal. The system calls upon an artificial intelligence model to refine and score the original deviant facts, which are then stored in the database after observer confirmation. Subsequently, the system categorizes the deviant facts according to basic functional competence dimensions and scores their severity, storing the categorization and scoring results. After confirming the deviant facts, the operator, guided by the system, collaborates with the observer to complete a root cause analysis. The system generates a basic functional competence map based on the categorization and scoring data, and a capability characteristic dimension map based on the root cause classification results, as well as group and individual data. Finally, the system recommends improvement measures based on the two types of maps and the root cause classification results, and tracks the effectiveness of the improvement measures.

[0085] Through the above implementation methods, this application can integrate the recording, improvement, evaluation, classification, scoring, root cause analysis, capability map generation, improvement measure recommendation, and improvement effect tracking of operator deviation facts into a continuous process, making operator capability evaluation more standardized, quantitative, and visualized, and improving the pertinence of capability weakness identification and improvement measure recommendation.

[0086] The present application has been described in detail above with reference to the embodiments. However, the present application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present application. All content not described in detail in this application can be derived from existing technology.

Claims

1. A method for evaluating operator competence based on the theory of individual differences, characterized in that, include: S1, Obtain facts of deviations by operators during training or work, wherein the facts of deviations include the five elements of deviation facts; S2, based on the five elements of deviation facts, automatically improves and evaluates the deviation facts, and generates improved deviation facts, fact completeness scores and scoring basis; S3, classify and score the improved deviation facts according to the ability dimensions to obtain the basic functional ability dimensions and scoring results corresponding to the deviation facts; S4. Based on the basic functional competence dimensions and the scoring results, calculate the operator's competence scores on multiple basic functional competence dimensions and generate an operator basic functional competence map. S5, perform root cause analysis on the aforementioned deviation facts to obtain the root cause classification results; S6. Based on the root cause classification results and the individual difference theory, and combining group data and individual data, calculate the evaluation results of the operator on multiple capability characteristic dimensions. S7. Based on the evaluation results on the capability characteristic dimensions, generate an operator capability characteristic dimension map; S8. Based on the basic functional capability map, the capability feature dimension map, and the root cause classification results, recommend measures to improve operator capabilities.

2. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, The five elements of the deviation fact mentioned in step S1 include background, people, operation, error point, and risk and consequences; wherein, the background is used to characterize the unit status, task execution or abnormal operating conditions, the people are used to characterize the person responsible for the behavior and their position, the operation is used to characterize the specific behavior of the person responsible and the tools or documents used, the error point is used to characterize the core deviation of the behavior that does not meet the job expectations or ability requirements, and the risk and consequences are used to characterize the risks or consequences that the error point may cause or has already caused.

3. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S2, which involves automatically improving and evaluating the deviation facts to generate improved deviation facts, fact completeness scores, and scoring criteria, includes: Build training and validation libraries for automatic fact-finding and evaluation of biases; The training library includes standardized deviation fact samples that meet the five elements of deviation facts, and the verification library includes deviation fact samples with missing, incorrect or incomplete content and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, so that the artificial intelligence model has the ability to complete biased facts, score fact integrity, and output scoring basis. The artificial intelligence model identifies the five missing or incomplete elements in the original deviation facts and outputs an evaluation result that includes a complete description of the deviation facts, a completeness score, and the basis for the score.

4. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, In step S3, the basic functional dimensions include six primary dimensions: monitoring, control, conservatism, teamwork, knowledge, and behavioral norms.

5. The operator competence evaluation method based on individual differences theory according to claim 4, characterized in that, Each of the aforementioned basic functional dimensions contains multiple secondary dimensions.

6. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, In step S3, the scoring results are categorized according to the severity of the deviation facts into good facts, expected facts, minor deviations, moderate deviations, and severe deviations. The first scoring interval corresponds to good facts, the second scoring interval corresponds to meeting expectations, the third scoring interval corresponds to minor deviations, the fourth scoring interval corresponds to moderate deviations, and the fifth scoring interval corresponds to serious deviations.

7. The operator competence evaluation method based on individual differences theory according to claim 6, characterized in that, The scoring results are based on a 5-point scale, where: The rating range for good facts is [4.5, 5]. The expected score range is [4, 4.5); The scoring range for slight deviations is [3.5, 4); The scoring range for general deviation is [3, 3.5); The scoring range for severe deviation is [0, 3).

8. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S3 includes: Construct training and validation libraries for ability dimension classification and scoring; The training library includes standardized bias fact samples with labeled basic functional dimensions and scoring results, and the validation library includes bias fact samples with classification or scoring bias and corresponding evaluation results. The artificial intelligence model is trained using the training library and validated and corrected using the validation library, enabling the artificial intelligence model to automatically classify and score biased facts based on their capability dimensions.

9. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S4 includes: Statistically analyze the target operator's multiple ratings within a preset time period according to the basic functional competence dimension; The ability score for the same basic functional competency dimension is obtained by averaging multiple ratings. The calculation formula is as follows: Where I represents the corresponding basic functional dimension, S I This represents the basic functional ability score for a certain dimension, where i represents the score number and s represents the score. i This represents the i-th rating result in the corresponding basic functional competence dimension, where n is the number of rating results in the corresponding basic functional competence dimension. A radar chart is generated based on the capability scores of multiple basic functional dimensions, serving as the basic functional capability map of the operator.

10. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S5 includes guiding observers and / or operators to perform analysis according to a preset root cause analysis process based on the confirmed deviation facts; and storing the root cause classification results in a database.

11. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, In step S6, the ability characteristic dimensions include execution ability, communication ability, judgment ability, learning ability, responsibility ability, and physical ability.

12. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S6 includes: Map the root cause classification results to the corresponding capability feature dimensions; The proportion of facts about weaknesses in each dimension of the statistical group to the total number of facts about the group (S) n ; The proportion of facts about the weaknesses of the target manipulator in each dimension of their competency characteristics to the total number of facts about the target manipulator (T) n ; The percentage of facts in the statistical group that deviate below expectations across all dimensions of ability characteristics, F. n ; The percentage of instances where the target manipulator's performance deviated below expectations across all capability characteristic dimensions out of the total number of instances involving that individual. n ; According to S n T n F n and f n Calculate the evaluation results P of the target operator on each dimension of capability characteristics. n The calculation formula is: Where 2 is the correction factor.

13. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S7 includes: evaluating the results P from multiple capability characteristic dimensions. n A radar chart is generated as a dimension map of the operator's capability characteristics.

14. The operator competence evaluation method based on individual differences theory according to claim 1, characterized in that, Step S8 includes: Identify the fundamental functional weaknesses in the fundamental functional capability map; Identify the capability feature weaknesses in the capability feature dimension map; Based on the basic functional weakness, the capability characteristic weakness, and the root cause classification result, at least one capability improvement measure is matched from the preset improvement measure library.

15. The operator competence evaluation method based on individual differences theory according to claim 14, characterized in that, Step S8 is followed by: Obtain improvement evaluation data after the operator implements the capability improvement measures; Update the operator's deviation fact data, basic functional strength map, and capability characteristic dimension map based on the improved evaluation data; Determine whether the improvement results have achieved the preset improvement goals. If not, recommend or adjust the capability improvement measures to form a closed loop of capability evaluation and improvement.

16. A system for evaluating operator competence based on the theory of individual differences, characterized in that, include: The deviation fact acquisition module is used to acquire deviation facts of operators during training or work, and the deviation facts include the five elements of deviation facts; The deviation fact improvement and evaluation module is used to automatically improve and evaluate the deviation fact based on the five elements of the deviation fact, and generate the improved deviation fact, fact completeness score and scoring basis; The capability dimension classification and scoring module is used to classify and score the improved deviation facts according to capability dimensions, and obtain the basic functional capability dimensions and scoring results corresponding to the deviation facts. The basic functional competence map generation module is used to calculate the operator's ability score on multiple basic functional competence dimensions based on the basic functional competence dimensions and the scoring results, and generate the operator's basic functional competence map. The root cause analysis module is used to perform root cause analysis on the deviation facts and obtain the root cause classification results; The competency characteristic evaluation module is used to calculate the evaluation results of operators on multiple competency characteristic dimensions based on the root cause classification results and individual difference theory, combined with group data and individual data. The capability feature map generation module is used to generate an operator capability feature dimension map based on the evaluation results on the capability feature dimensions. The improvement measure recommendation module is used to recommend operator capability improvement measures based on the basic functional capability map, the capability feature dimension map, and the root cause classification results.

17. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The five elements of the deviation include background, people, operation, point of error, and risk and consequences; The background is used to characterize the unit status, task execution, or abnormal operating conditions; the person is used to characterize the person responsible for the action and their position; the operation is used to characterize the specific behavior of the person responsible and the tools or documents used; the error point is used to characterize the core deviation of the behavior from the job expectations or ability requirements; and the risk and consequence are used to characterize the risk or consequence that the error point may cause or has already caused.

18. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The deviation fact improvement assessment module includes: The first training library construction unit is used to construct a training library for automatic improvement and evaluation of biased facts. The training library includes standardized biased fact samples that meet the requirements of the five elements of biased facts. The first verification library construction unit is used to construct a verification library for automatic improvement and evaluation of deviation facts. The verification library includes deviation fact samples with missing, incorrect or incomplete content and corresponding evaluation results. The first model training and verification unit is used to train an artificial intelligence model using the training library and to verify and correct the artificial intelligence model using the verification library, so that the artificial intelligence model has the ability to complete biased facts, score fact integrity, and output scoring basis. The deviation fact output unit is used to identify the five missing or incomplete elements in the original deviation fact by the artificial intelligence model, and output the evaluation result including the improved deviation fact description, completeness score and scoring basis.

19. A operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The basic functional competency dimensions used in the competency dimension classification and scoring module include six primary dimensions: monitoring, control, conservatism, teamwork, knowledge, and behavioral norms.

20. The operator competence evaluation system based on individual differences theory according to claim 19, characterized in that, Each of the aforementioned basic functional dimensions contains multiple secondary dimensions.

21. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The capability dimension classification and scoring module is used to classify the scoring results into good facts, expected facts, minor deviations, moderate deviations, and severe deviations according to the severity of the deviation facts; The first scoring interval corresponds to good facts, the second scoring interval corresponds to meeting expectations, the third scoring interval corresponds to minor deviations, the fourth scoring interval corresponds to moderate deviations, and the fifth scoring interval corresponds to serious deviations.

22. The operator competence evaluation system based on individual differences theory according to claim 21, characterized in that, The scoring results are based on a 5-point scale, where: The rating range for good facts is [4.5, 5]. The expected score range is [4, 4.5); The scoring range for slight deviations is [3.5, 4); The scoring range for general deviation is [3, 3.5); The scoring range for severe deviation is [0, 3).

23. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The capability dimension classification and scoring module includes: The second training library construction unit is used to construct a training library for ability dimension classification and scoring. The training library includes normalized bias fact samples with labeled basic functional ability dimensions and scoring results. The second verification library construction unit is used to construct a verification library for ability dimension classification and scoring. The verification library includes bias fact samples with classification or scoring bias and corresponding evaluation results. The second model training and verification unit is used to train the artificial intelligence model using the training library and to verify and correct the artificial intelligence model using the verification library, so that the artificial intelligence model can automatically classify and score the biased facts according to the capability dimension.

24. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The basic functional competence map generation module is used to statistically analyze multiple rating results of the target operator within a preset time period according to the basic functional competence dimensions, and to calculate the average of multiple rating results under the same basic functional competence dimension to obtain the competence score for that basic functional competence dimension. The calculation formula is as follows: Where I represents the corresponding basic functional dimension, S I This represents the basic functional ability score for a certain dimension, where i represents the score number and s represents the score. i This represents the i-th rating result in the corresponding basic functional competence dimension, where n is the number of rating results in the corresponding basic functional competence dimension. The basic functional competence map generation module is also used to generate a radar map based on the capability scores of multiple basic functional competence dimensions, which serves as the operator's basic functional competence map.

25. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The root cause analysis module is used to guide observers and / or operators to conduct analysis according to a preset root cause analysis process based on confirmed deviation facts, and to store the root cause classification results in a database.

26. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The competency evaluation module uses competency dimensions including execution, communication, judgment, learning, responsibility, and physical ability.

27. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The capability characteristic evaluation module is used for: Map the root cause classification results to the corresponding capability feature dimensions; The proportion of facts about weaknesses in each dimension of the statistical group to the total number of facts about the group (S) n ; The proportion of facts about the weaknesses of the target manipulator in each dimension of their competency characteristics to the total number of facts about the target manipulator (T) n ; The percentage of facts in the statistical group that deviate below expectations across all dimensions of ability characteristics, F. n ; The percentage of instances where the target manipulator's performance deviated below expectations across all capability characteristic dimensions out of the total number of instances involving that individual. n ; According to S n T n F n and f n Calculate the evaluation results P of the target operator on each dimension of capability characteristics. n The calculation formula is: Where 2 is the correction factor.

28. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The capability feature map generation module is used to generate evaluation results P from multiple capability feature dimensions. n A radar chart is generated as a dimension map of the operator's capability characteristics.

29. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The improvement recommendation module is used for: Identify the fundamental functional weaknesses in the fundamental functional capability map; Identify the capability feature weaknesses in the capability feature dimension map; Based on the basic functional weakness, the capability characteristic weakness, and the root cause classification result, at least one capability improvement measure is matched from the preset improvement measure library.

30. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The system also includes an improved closed-loop management module, which is used for: Obtain improvement evaluation data after the operator implements the capability improvement measures; Update the operator's deviation fact data, basic functional strength map, and capability characteristic dimension map based on the improved evaluation data; Determine whether the improvement results have achieved the preset improvement goals. If not, recommend or adjust the capability improvement measures to form a closed loop of capability evaluation and improvement.

31. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The system also includes a data storage module, which is used to store deviation fact data, improved deviation facts, fact integrity scores, scoring basis, basic functional dimension, scoring results, root cause classification results, capability characteristic dimension evaluation results, basic functional map, capability characteristic dimension map, and capability improvement measure data.

32. The operator competence evaluation system based on individual differences theory according to claim 16, characterized in that, The system also includes a data display module, which is used to display the basic functional capability map and the capability characteristic dimension map according to the operator, and to display relevant evaluation data in the process of operator capability improvement.

Images