A power operation VR training operation process adaptability evaluation method

Abstract

The application discloses a kind of electric power operation VR training operation process adaptability evaluation method and equipment, it is related to electric power operation training technical field, comprising: through multi-source perception equipment acquisition VR training multidimensional data of whole process and label processing;Multi-dimensional evaluation index system covering process compliance, scene adaptability, capability matching is constructed;Based on improved multi-criteria decision algorithm and fuzzy evaluation algorithm, a dynamic evaluation model is constructed, quantitative scoring is realized;Short board of adaptability is identified and evaluation report is generated;Linkage intelligent recommendation engine pushes targeted training content;Establish data iteration updating mechanism and continuously optimize model.The application also discloses corresponding evaluation equipment and computer readable storage medium, realizes the overall, accurate, dynamic evaluation of electric power operation VR training operation process, provides scientific support for individualized training, significantly improves training quality and efficiency, and creatively breaks through the limitations of traditional evaluation.

Description

Technical Field

[0001] This invention relates to the field of power operation training technology, and in particular to a method for assessing the adaptability of VR training operation procedures for power operations. Background Technology

[0002] With the deep application of digital and intelligent technologies in the power industry, VR training has become a core means to improve the skills of power workers, widely covering 17 types of special power operation training scenarios, including high-voltage electricians, high-altitude operations, and confined space operations. However, existing VR training assessment methods for power operations have several significant shortcomings: First, the assessment dimensions are singular, focusing primarily on the success of the operation, neglecting the compliance of the operational procedures, scenario adaptability, and the match with the individual abilities of the trainees, thus failing to comprehensively reflect the core issues of the training. Second, the assessment indicators are fixed and rigid, failing to be differentiated based on the risk level, job differences, and scenario complexity of power operations, resulting in poor scenario adaptability. Third, assessment and training are disconnected, lacking an effective linkage mechanism; assessment results cannot directly support the generation of personalized training programs, and training optimization lacks scientific data support. Fourth, the assessment model is static, lacking a continuous iteration and update mechanism, unable to adapt to dynamic changes such as updates to industry safety regulations and improvements in trainees' skill levels, making it difficult to consistently guarantee assessment accuracy. Fifth, the presentation of assessment results is monotonous, lacking intuitive visualization, which is not conducive to training managers quickly identifying overall shortcomings and individual differences. Summary of the Invention

[0003] The purpose of this invention is to address the problems existing in the background art by proposing an adaptability assessment method for VR training operation procedures in power operations.

[0004] The technical solution of this invention: A method for adaptability assessment of VR training operation process for power operations, comprising the following steps: S1: Collect multi-dimensional data of the entire process of VR training for power operations through multi-source sensing devices; S2: Construct a multi-dimensional adaptability evaluation index system. The index system includes at least the process compliance dimension, scenario adaptability dimension, and capability matching dimension. Several dynamically adjustable evaluation indicators are configured under each dimension. S3: Based on the improved multi-criteria decision-making algorithm, determine the weight coefficients of each evaluation index, and construct a dynamic evaluation model by combining the fuzzy evaluation algorithm. Input the multi-dimensional data after labeling into the model for quantitative calculation to obtain the comprehensive score of the adaptability of the operation process and the sub-item scores of each dimension. S4: Based on the comprehensive score and sub-item score results, identify the adaptability shortcomings in the operation process and generate an evaluation report that includes the location of the shortcomings, cause analysis and improvement directions. S5: Link the assessment report with the intelligent recommendation engine to push targeted and optimized training content from the customized training resource library based on the information on shortcomings and the job characteristics and ability baseline of the trainees; S6: Establish an iterative update mechanism for assessment data, continuously collect subsequent operational data, assessment feedback data, and industry standard update data from trainees, and dynamically optimize the weights of assessment indicators, evaluation rules, and assessment model parameters.

[0005] Preferably, in step S1, the multi-source sensing device includes a VR interactive device with position tracking function, a motion capture system, a physiological sensing device and a scene feedback acquisition unit. The multi-dimensional data includes operation behavior data, process execution data, device interaction data, physiological response data and scene adaptation feedback data, and the data is labeled according to a preset classification rule.

[0006] Preferably, in step S1, the operation behavior data includes operation trajectory feature data, movement amplitude parameters, and operation speed distribution data; the process execution data includes step completion time sequence data, step omission statistics, repeated operation frequency data, and key step execution duration data; the device interaction data includes VR simulation device operation force data, state switching response data, and interaction command accuracy data; the physiological response data includes heart rate fluctuation data, movement stability data, and stress response duration data; and the tagging process adopts a three-dimensional tagging system.

[0007] Preferably, in step S2, the evaluation indicators for the process compliance dimension include, but are not limited to, step completeness indicators, operation sequence compliance indicators, key action standardization indicators, safety procedure conformity indicators, and operation specification compliance indicators; the evaluation indicators for the scenario adaptability dimension include, but are not limited to, complex working condition handling capability indicators, sudden risk handling effectiveness indicators, equipment status adaptability indicators, environmental factor adaptability indicators, and multi-scenario switching adaptability indicators; the evaluation indicators for the capability matching dimension include, but are not limited to, operation proficiency indicators, decision rationality indicators, emergency response speed indicators, error correction efficiency indicators, and skill transferability indicators.

[0008] Preferably, in step S3, the improved multi-criteria decision-making algorithm is an analytic hierarchy process (AHP), entropy weighting method, or combined weighting method that introduces a consistency correction mechanism. The weight coefficients are configured differently according to the risk level, job type, and training objectives of the power operation. The fuzzy evaluation algorithm establishes an index fuzzy evaluation matrix, defines multi-level evaluation levels, and uses a weighted average operator or fuzzy synthesis operator to calculate the fit scores of each dimension and the overall performance.

[0009] Preferably, in step S5, the intelligent recommendation engine performs precise matching based on the trainee's competency profile and shortcomings. The customized training resource library includes, but is not limited to, VR practical training scenarios, theoretical knowledge courses, accident case analysis resources, operation specification demonstration videos, and interactive exercise resources. The pushed content can be dynamically adjusted according to the training effect.

[0010] Preferably, in step S6, the iterative update mechanism includes: collecting new training data samples at a preset cycle, with the sample size meeting the statistical requirements for model optimization; recalibrating the weights of the evaluation indicators based on the new data; updating the evaluation thresholds and rules of the evaluation indicators in conjunction with the latest industry safety regulations and work standards; and adjusting the evaluation benchmark of the competency matching dimension based on the job promotion data and skill level certification data of the trainees.

[0011] An adaptive assessment device for VR training operation process in power operations includes: a multi-source data acquisition module: used to acquire multi-dimensional data of the entire VR training process in power operations through multi-source sensing devices, and equipped with a data tagging processing unit to realize three-dimensional tag generation and data classification; Evaluation indicator configuration module: It has a built-in multi-dimensional adaptable evaluation indicator system, supports dynamic addition, deletion, definition modification and weight coefficient configuration of evaluation indicators, and stores indicator configuration schemes corresponding to different work types and risk levels. Dynamic evaluation calculation module: integrates an improved multi-criteria decision-making algorithm unit and a fuzzy evaluation algorithm unit, used to realize the calculation of evaluation index weights, multi-dimensional data quantitative analysis and adaptation score generation; Assessment report generation module: used to identify adaptability shortcomings, generate structured assessment reports, and support personalized configuration of report content and export in multiple formats; Intelligent Linkage Recommendation Module: Equipped with an intelligent recommendation engine, it establishes data interaction with a customized training resource library to achieve precise delivery and dynamic adjustment of targeted training content; Model Iteration and Optimization Module: Used to collect various types of data required for iterative updates, and to calibrate the weights of evaluation indicators, update evaluation rules, and optimize the parameters of the evaluation model.

[0012] Preferably, the multi-source data acquisition module is connected to the VR interactive device, motion capture system, and physiological sensing device through an industrial-grade communication interface, supporting adaptation to multiple industrial communication protocols such as RS485, RSCAN, and Ethernet. The dynamic evaluation calculation module uses a high-performance processing chip, which supports parallel computing and real-time evaluation, with an evaluation calculation latency of ≤1s. The intelligent linkage recommendation module establishes a linkage interface with the smart training management platform and the VR training equipment management system to realize one-click push of training content and feedback of training effect data.

[0013] Compared with existing technologies, the advantages of this invention are as follows: This invention overcomes the limitations of traditional VR training and assessment in power operations, such as single-dimensional assessment, rigid models, and insufficient linkage with training. By constructing a multi-dimensional configurable indicator system encompassing process compliance, scenario adaptability, and capability matching, and combining an improved combined weighting method with a fuzzy comprehensive evaluation algorithm, it integrates the experience of power industry experts and the characteristics of job risks while relying on objective data laws to achieve comprehensive and accurate assessment results. Furthermore, through deep linkage between assessment and an intelligent recommendation engine, a closed-loop management system is formed, accurately pushing suitable training content and significantly improving the relevance and efficiency of training. Attached Figure Description

[0014] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a structural block diagram of an adaptive assessment device for VR training operation procedures in power operations, as proposed in this invention. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0017] It should be noted that the following description covers various aspects of embodiments within the scope of the appended claims. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0018] Firstly, this invention provides a method for assessing the adaptability of VR training procedures for power operations, such as... Figure 1 As shown, the process includes the following steps: S1: Collect multi-dimensional data of the entire process of VR training for power operations through multi-source sensing devices; Specifically, in step S1, the multi-source sensing device includes a VR interactive device with position tracking function, a motion capture system, a physiological sensing device and a scene feedback acquisition unit. The multi-dimensional data includes operation behavior data, process execution data, device interaction data, physiological response data and scene adaptation feedback data, and the data is labeled according to a preset classification rule. Furthermore, the operational behavior data includes operational trajectory feature data, motion amplitude parameters, and operational speed distribution data; the process execution data includes step completion time sequence data, step omission statistics, repeated operation frequency data, and key step execution duration data; the device interaction data includes VR simulation device operation force data, state switching response data, and interaction command accuracy data; the physiological response data includes heart rate fluctuation data, motion stability data, and stress response duration data; and the tagging processing adopts a three-dimensional tagging system.

[0019] It should also be noted that step S1 comprehensively captures data from the entire VR training process for power operations using multiple types of sensing devices to ensure the comprehensiveness and accuracy of the evaluation data. Specifically, the devices used are VR interactive devices with position tracking capabilities, such as VR headsets, controllers, with a single-eye resolution ≥1440x1700, 3DOF / 6DOF motion capture systems, wearable physiological sensing devices such as heart rate sensors, motion stability sensors, and scene feedback acquisition units such as VR scene built-in interactive feedback modules.

[0020] In this embodiment, when collecting operation behavior data, it is collected through a VR position tracking and motion capture system, including operation trajectory feature data (three-dimensional coordinate trajectory, trajectory curvature), motion amplitude parameters (limb movement angle, operation force range), and operation speed distribution data (average operation speed, peak speed of key movements). When collecting process execution data, record the execution status of operation steps during training, including step completion time sequence data (start and end time of each step, interval between steps), step omission statistics (number of omission steps, percentage of omission of key steps), repetitive operation frequency data (number of times the same step is repeated), and key step execution time data (time consumed by core operation steps). When collecting device interaction data, the interaction information between the training subject and the VR simulation device is collected, including operation force data (obtained through the pressure sensor of the controller), state switching response data (device mode switching delay, command response time), and interaction command accuracy data (the degree of matching between the operation command and the expected command). When collecting physiological response data, wearable physiological sensors are used to collect data including heart rate fluctuation data (the difference between resting heart rate and heart rate during operation, and the coefficient of variation of heart rate), movement stability data (the amplitude and frequency of limb shaking during operation), and stress response duration data (the delay in operation response under sudden scenarios). When collecting scenario adaptation feedback data, the data is collected through the built-in feedback module of the VR scenario, including the trainees' response feedback scores and subjective adaptation evaluations to scenarios such as complex working conditions, sudden risks, and environmental changes.

[0021] In addition, after the data collection is completed, the data is tagged according to the three-dimensional tagging system of "operation category, operation stage, and data attribute", such as "high voltage electrician, power outage and restoration operation, operation trajectory data" and "confined space operation, rescue stage, physiological response data", to provide structured data support for subsequent evaluation.

[0022] S2: Construct a multi-dimensional adaptability evaluation index system. The index system includes at least the process compliance dimension, scenario adaptability dimension, and capability matching dimension. Several dynamically adjustable evaluation indicators are configured under each dimension. Specifically, in step S2, the evaluation indicators for the process compliance dimension include, but are not limited to, step completeness indicators, operation sequence compliance indicators, key action standardization indicators, safety procedure fit indicators, and operation specification compliance indicators; the evaluation indicators for the scenario adaptability dimension include, but are not limited to, complex working condition handling capability indicators, sudden risk handling effectiveness indicators, equipment status adaptability indicators, environmental factor adaptability indicators, and multi-scenario switching adaptability indicators; the evaluation indicators for the capability matching dimension include, but are not limited to, operation proficiency indicators, decision rationality indicators, emergency response speed indicators, error correction efficiency indicators, and skill transferability indicators.

[0023] This step breaks through the limitations of traditional single-indicator evaluation and constructs a multi-dimensional, configurable indicator system covering "processes, scenarios, and capabilities": First, by focusing on the degree of conformity between the operating procedures and the safety regulations and operating specifications of the power industry, the configured evaluation indicators include, but are not limited to, the step completeness indicator (the degree of conformity between the actual completed steps and the standard steps), the operation sequence conformity indicator (the degree of matching between the operation steps and the standard sequence), the key action standardization indicator (the similarity between the core operation actions and the standardized actions), the safety regulation conformity indicator (the degree of conformity between the operation behavior and industry standards such as DL408-91), and the operation specification compliance indicator (the degree of implementation of the company's internal operating rules). Subsequently, the focus is on the adaptability of the operating procedures to different training scenarios. The configured evaluation indicators include, but are not limited to, indicators for handling complex working conditions (operational adaptability to complex scenarios such as multi-device collaboration and cross-operations), indicators for the effectiveness of handling sudden risks (the rationality of the response procedures to sudden scenarios such as equipment failure and safety hazards), indicators for equipment status adaptability (the degree of operational adaptability to different models and states of simulation equipment), indicators for environmental factor adaptability (operational stability in virtual environments such as high temperature, humidity, and severe weather), and indicators for adaptability to switching between multiple scenarios (the speed of recovery of operational proficiency after switching between different work scenarios). Finally, the assessment indicators, including but not limited to, are designed to match the individual trainees' abilities with the operational procedures, including: operational proficiency indicators (operation time, error rate, frequency of repetitive operations); decision-making rationality indicators (the scientific nature of work plan selection and risk assessment); emergency response speed indicators (operation response time in emergency scenarios, speed of initiation of handling procedures); error correction efficiency indicators (correction time after discovering operational errors, rationality of correction steps); and skill transferability indicators (the effectiveness of transferring operational abilities from simple to complex scenarios). Each dimension of indicators supports dynamic addition, deletion, and definition modification to adapt to the assessment needs of different types of power operations.

[0024] S3: Based on the improved multi-criteria decision-making algorithm, determine the weight coefficients of each evaluation index, and construct a dynamic evaluation model by combining the fuzzy evaluation algorithm. Input the multi-dimensional data after labeling into the model for quantitative calculation to obtain the comprehensive score of the adaptability of the operation process and the sub-item scores of each dimension. Specifically, in step S3, the improved multi-criteria decision-making algorithm is an analytic hierarchy process (AHP), entropy weighting method, or combined weighting method that introduces a consistency correction mechanism. The weight coefficients are configured differently according to the risk level, job type, and training objectives of the power operation. The fuzzy evaluation algorithm establishes an index fuzzy evaluation matrix, defines multi-level evaluation levels, and uses a weighted average operator or fuzzy synthesis operator to calculate the fit scores of each dimension and the overall performance.

[0025] In this embodiment, the specific steps for constructing the dynamic evaluation model are as follows: S100: Standardize and normalize the multi-dimensional data after labeling in S1 to eliminate the differences in the units of different indicator data (such as different units for operation time, heart rate fluctuation, and movement amplitude) and ensure that the data is comparable. It should be noted that the standardization process uses different formulas to convert positive indicators (higher scores are better, such as operational accuracy) and negative indicators (lower scores are better, such as the number of errors). The specific formulas are as follows: Standardized formula for positive indicators: ; in, Let be the standardized value of the j-th indicator for the i-th training subject (within the range [0,1]). For the j-th indicator of the i-th training subject, These are the maximum and minimum values ​​of the j-th indicator for all training participants, respectively. Standardization formula for negative indicators: ; Subsequently, the standardized data is normalized to ensure that the data distribution of each indicator is consistent, as shown in the following formula: ; in, Let be the normalized value of the j-th indicator for the i-th training subject, and n be the number of training subjects in the sample.

[0026] S200: Employs a combined weighting strategy of subjective weights (improved AHP) and objective weights (entropy weighting method), which reflects the differentiated needs of power operation risk levels and job types while avoiding the one-sidedness of a single weighting method, including: S201: Subjective weight calculation (improved AHP method), introducing a consistency correction mechanism to solve the consistency deviation problem of the traditional AHP judgment matrix. The steps are as follows: Constructing a judgment matrix: Invite k power industry safety training experts and senior operators (k≥5) to conduct pairwise comparisons of the importance of indicators within the same dimension, based on DL408-91 "Power Safety Work Regulations" and job risk levels. A 1-9 scale (1 = equally important, 3 = slightly important, 5 = significantly important, 7 = strongly important, 9 = extremely important, 2 / 4 / 6 / 8 are median values) is used to construct the judgment matrix. Specifically: ; Where m is the number of indicators in this dimension. Let p-th indicator be the importance scale relative to q-th indicator, satisfying... (reciprocity) (Reflexivity); Initial weight calculation: The eigenvectors of the judgment matrix, i.e., the initial subjective weights, are calculated using the sum-product method. The calculation formula is: ; in, Let p be the initial subjective weight of the p-th indicator. To determine the sum of the elements in the q-th column of a matrix; Consistency Check and Correction: Introducing a Consistency Correction Factor To ensure the logical rationality of the judgment matrix: Calculate the consistency index (CI): ; in, To determine the largest eigenvalue of a matrix, For matrix A and vector The p-th element of the product; Find the average random consistency index RI (determined by the value of m, e.g., RI = 1.12 when m = 5), and calculate the consistency ratio CR: ; If CR ≤ 0.1, the judgment matrix satisfies the consistency requirement, and the initial weights are... Effective; if CR > 0.1, introduce a correction factor. Adjust the elements of the judgment matrix Repeat steps 2-3 until CR ≤ 0.1, and finally obtain the corrected subjective weight. .

[0027] S202: Objective weight calculation (entropy weight method): Objective weights are extracted based on the dispersion of the data itself, reflecting the information contribution of the indicators. The steps are as follows: Constructing an indicator data matrix: using normalized indicator data Construct the matrix: .

[0028] The formula for calculating the entropy value of the index is as follows: ; in, Let j be the entropy value of the j-th index (range [0,1]). To avoid The smallest value is the logarithmically meaningless minimum value. The smaller the entropy value, the greater the dispersion of the indicator data, the richer the information content, and the higher the weight should be.

[0029] The objective weights are calculated using the following formula: ; in, Let j be the objective weight of the j-th indicator. The coefficient of variation of the indicator reflects the indicator's ability to distinguish the evaluation results.

[0030] S203: Combined weight fusion, using a weighted summation method to fuse subjective and objective weights, taking into account both expert experience and objective data patterns, the formula is as follows: ; in, The final combined weight of the j-th indicator (satisfying) ), This is a weighting coefficient (range [0.4, 0.6]), which can be dynamically adjusted according to the type of electrical work: high-risk work (such as high-voltage electricians, confined space work) takes... Strengthen the weighting of expert experience in safety-related indicators; for ordinary operations... Highlighting the objective laws of data.

[0031] S300: Based on the power industry training evaluation standards, a fuzzy evaluation matrix is ​​constructed to quantify the suitability level of various indicators for training participants, including the following steps: S301: Determine the evaluation level: Define five evaluation levels: "Excellent, Good, Satisfactory, Basically Satisfactory, Unsatisfactory", corresponding to the scoring ranges [90,100], [80,89], [60,79], [40,59], and [0,39]. Let the set of evaluation levels be denoted as . .

[0032] S302: Calculate membership degree: Use the trapezoidal membership function to calculate the membership degree of the j-th indicator for the i-th training subject belonging to the k-th evaluation level. The formula is as follows (taking a positive indicator as an example): when (Corresponding to "Unqualified") ,the remaining ; when (Corresponding to "Basic Qualified") ,the remaining ; when (Corresponding to "Qualified") ,the remaining ; when (Corresponding to "good") ,the remaining ; when (Corresponding to "Excellent") ,the remaining ; in, Membership degree (value range [0,1]) reflects the degree of fit between the indicator data and the evaluation level, satisfying... .

[0033] S303: Constructing the fuzzy evaluation matrix: Arrange the membership degrees in order of indicators to form the fuzzy evaluation matrix of the i-th training object. In the matrix, each row corresponds to one indicator, and each column corresponds to one evaluation level.

[0034] S400: Fuzzy synthesis computation, employing a weighted average fuzzy synthesis operator. Combining the combined weights and the fuzzy evaluation matrix, the fuzzy evaluation vectors for each dimension and the overall fit are calculated, as follows: ; in, Let be the fuzzy evaluation vector for the i-th training subject. This is the weight vector of the indicator combination, and "∘" represents the fuzzy composition operation, specifically calculated as follows: , Let the comprehensive membership degree of the i-th training subject belong to the k-th evaluation level be such that it satisfies This reflects the overall suitability of the trainees and the degree of fit between each evaluation level.

[0035] S500: Rating level conversion, using a combination of the maximum membership principle and weighted average method, transforms fuzzy evaluation vectors into specific quantitative scores: Determine the dominant evaluation level: Select the evaluation level with the highest overall membership degree. As the dominant level, that is ; Calculate the quantitative score: Assign a midpoint value to each evaluation level (Excellent 95 points, Good 85 points, Pass 70 points, Basic Pass 50 points, Fail 20 points), and calculate the final score using a weighted average method, as shown in the formula below: ; in, The overall score for the adaptability of the operation process to the i-th training subject (out of 100 points). This is the midpoint value of the k-th evaluation level; Sub-item score calculation: For the three dimensions of process compliance, scenario adaptability, and capability matching, repeat steps S200-S500 respectively to calculate the sub-item score of each dimension, providing data support for identifying shortcomings.

[0036] S4: Based on the comprehensive score and sub-item score results, identify the adaptability shortcomings in the operation process and generate an evaluation report that includes the location of the shortcomings, cause analysis and improvement directions. In this embodiment, a multi-dimensional weakness analysis is conducted based on the overall score and the scores of each dimension's sub-items, including: Dimensional weakness identification: If the score of a certain dimension is lower than the preset threshold (such as the passing score of 60 points), then the dimension is determined to be the overall weakness. For example, if the score of the scenario adaptability dimension is 55 points, it indicates that the trainee's operational adaptability in different scenarios is insufficient. Indicator-level weakness identification: For specific indicators with low scores in each dimension, pinpoint the weaknesses precisely. For example, in the process compliance dimension, the "standardization of key actions" indicator score of 58 points indicates that the core operation actions are not standardized. Cause analysis: Combining the job background of the trainees, training history data, and operational process details, we analyzed the causes of the shortcomings, including poor memory of safety procedures, lack of practical experience, insufficient training in dealing with emergencies, and weak individual decision-making ability. Evaluation Report Generation: Generates a structured evaluation report, including a comprehensive score and grade, scores for each dimension, identification of weaknesses (dimension level + indicator level), causal analysis, and targeted improvement directions (such as strengthening practical training of key actions and increasing simulation training of complex scenarios). It supports exporting in multiple formats such as PDF, Word, and Excel.

[0037] S5: Link the assessment report with the intelligent recommendation engine to push targeted and optimized training content from the customized training resource library based on the information on shortcomings and the job characteristics and ability baseline of the trainees; Specifically, the intelligent recommendation engine performs precise matching based on the trainees' ability profiles and weaknesses. The customized training resource library includes, but is not limited to, VR practical training scenarios, theoretical knowledge courses, accident case analysis resources, operation specification demonstration videos, and interactive exercise resources. The pushed content can be dynamically adjusted according to the training effect.

[0038] S6: Establish an iterative update mechanism for assessment data, continuously collect subsequent operational data, assessment feedback data, and industry standard update data from trainees, and dynamically optimize the weights of assessment indicators, evaluation rules, and assessment model parameters.

[0039] Secondly, refer to Figure 2 The present invention also discloses an adaptive assessment device for the operation process of VR training for power operations, comprising: a multi-source data acquisition module: used to acquire multi-dimensional data of the entire process of VR training for power operations through multi-source sensing devices, and equipped with a data tagging processing unit to realize three-dimensional tag generation and data classification; Specifically, the multi-source data acquisition module integrates VR data acquisition units, motion data acquisition units, physiological data acquisition units, and scene feedback acquisition units; it establishes connections with VR interactive devices, motion capture systems, and physiological sensing devices through industrial-grade communication interfaces (RS485, Ethernet), supporting adaptation to multiple industrial communication protocols; the acquisition frequency is ≥10Hz, and the data transmission latency is ≤50ms; it is equipped with a data tagging processing unit to automatically complete the generation of three-dimensional tags for "job category, operation stage, and data attributes" and data classification.

[0040] Evaluation indicator configuration module: It has a built-in multi-dimensional adaptable evaluation indicator system, supports dynamic addition, deletion, definition modification and weight coefficient configuration of evaluation indicators, and stores indicator configuration schemes corresponding to different work types and risk levels. Dynamic evaluation calculation module: integrates an improved multi-criteria decision-making algorithm unit and a fuzzy evaluation algorithm unit, used to realize the calculation of evaluation index weights, multi-dimensional data quantitative analysis and adaptation score generation; Assessment report generation module: used to identify adaptability shortcomings, generate structured assessment reports, and support personalized configuration of report content and export in multiple formats; Intelligent Linkage Recommendation Module: Equipped with an intelligent recommendation engine, it establishes data interaction with a customized training resource library to achieve precise delivery and dynamic adjustment of targeted training content; Model Iteration and Optimization Module: Used to collect various types of data required for iterative updates, and to calibrate evaluation index weights, update evaluation rules, and optimize evaluation model parameters. Specifically, the iterative update mechanism includes: collecting new training data samples at a preset cycle, with the sample size meeting the statistical requirements for model optimization; recalibrating the weights of evaluation indicators based on the new data; updating the evaluation thresholds and rules of evaluation indicators in conjunction with the latest industry safety regulations and operating standards; and adjusting the evaluation benchmarks of the competency matching dimension based on the job promotion data and skill level certification data of the trainees.

[0041] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for assessing the adaptability of VR training operation procedures for power operations, characterized in that, Includes the following steps: S1: Collect multi-dimensional data of the entire process of VR training for power operations through multi-source sensing devices; S2: Construct a multi-dimensional adaptability evaluation index system. The index system includes at least the process compliance dimension, scenario adaptability dimension, and capability matching dimension. Several dynamically adjustable evaluation indicators are configured under each dimension. S3: Based on the improved multi-criteria decision-making algorithm, determine the weight coefficients of each evaluation index, and construct a dynamic evaluation model by combining the fuzzy evaluation algorithm. Input the multi-dimensional data after labeling into the model for quantitative calculation to obtain the comprehensive score of the adaptability of the operation process and the sub-item scores of each dimension. S4: Based on the comprehensive score and sub-item score results, identify the adaptability shortcomings in the operation process and generate an evaluation report that includes the location of the shortcomings, cause analysis and improvement directions. S5: Link the assessment report with the intelligent recommendation engine to push targeted and optimized training content from the customized training resource library based on the information on shortcomings and the job characteristics and ability baseline of the trainees; S6: Establish an iterative update mechanism for assessment data, continuously collect subsequent operational data, assessment feedback data, and industry standard update data from trainees, and dynamically optimize the weights of assessment indicators, evaluation rules, and assessment model parameters.

2. The method for adaptability assessment of VR training operation process for power operations according to claim 1, characterized in that, In step S1, the multi-source sensing device includes a VR interactive device with position tracking function, a motion capture system, a physiological sensing device and a scene feedback acquisition unit. The multi-dimensional data includes operation behavior data, process execution data, device interaction data, physiological response data and scene adaptation feedback data, and the data is labeled according to a preset classification rule.

3. The method for adaptability assessment of VR training operation process for power operations according to claim 2, characterized in that, The operational behavior data includes operational trajectory feature data, motion amplitude parameters, and operational speed distribution data; the process execution data includes step completion time sequence data, step omission statistics, repeated operation frequency data, and key step execution duration data; the device interaction data includes VR simulation device operation force data, state switching response data, and interaction command accuracy data; the physiological response data includes heart rate fluctuation data, motion stability data, and stress response duration data; the tagging process adopts a three-dimensional tagging system.

4. The method for adaptability assessment of VR training operation process for power operations according to claim 1, characterized in that, In step S2, the evaluation indicators for the process compliance dimension include, but are not limited to, step completeness indicators, operation sequence compliance indicators, key action standardization indicators, safety procedure fit indicators, and operation specification compliance indicators; the evaluation indicators for the scenario adaptability dimension include, but are not limited to, complex working condition response capability indicators, sudden risk handling effectiveness indicators, equipment status adaptability indicators, environmental factor adaptability indicators, and multi-scenario switching adaptability indicators; the evaluation indicators for the capability matching dimension include, but are not limited to, operation proficiency indicators, decision rationality indicators, emergency response speed indicators, error correction efficiency indicators, and skill transferability indicators.

5. The method for adaptability assessment of VR training operation process for power operations according to claim 1, characterized in that, In step S3, the improved multi-criteria decision-making algorithm is an analytic hierarchy process (AHP), entropy weighting method, or combined weighting method that introduces a consistency correction mechanism. The weight coefficients are configured differently according to the risk level, job type, and training objectives of the power operation. The fuzzy evaluation algorithm establishes an index fuzzy evaluation matrix, defines multi-level evaluation levels, and uses a weighted average operator or fuzzy synthesis operator to calculate the fit scores of each dimension and the overall performance.

6. The method for adaptability assessment of VR training operation process for power operations according to claim 1, characterized in that, In step S5, the intelligent recommendation engine performs precise matching based on the trainee's competency profile and shortcomings. The customized training resource library includes, but is not limited to, VR practical training scenarios, theoretical knowledge courses, accident case analysis resources, operation specification demonstration videos, and interactive exercise resources. The pushed content can be dynamically adjusted according to the training effect.

7. The method for adaptability assessment of VR training operation process for power operations according to claim 1, characterized in that, In step S6, the iterative update mechanism includes: collecting new training data samples at a preset cycle, with the sample size meeting the statistical requirements for model optimization; recalibrating the weights of the evaluation indicators based on the new data; updating the evaluation thresholds and rules of the evaluation indicators in conjunction with the latest industry safety regulations and work standards; and adjusting the evaluation benchmark of the competency matching dimension based on the job promotion data and skill level certification data of the trainees.

8. A device for assessing the adaptability of VR training operation procedures for power operations, employing the method for assessing the adaptability of VR training operation procedures for power operations as described in any one of claims 1-7, characterized in that, include: Multi-source data acquisition module: Used to collect multi-dimensional data of the entire process of power operation VR training through multi-source sensing devices, and equipped with a data tagging processing unit to realize three-dimensional tag generation and data classification; Evaluation indicator configuration module: It has a built-in multi-dimensional adaptable evaluation indicator system, supports dynamic addition, deletion, definition modification and weight coefficient configuration of evaluation indicators, and stores indicator configuration schemes corresponding to different work types and risk levels. Dynamic evaluation calculation module: integrates an improved multi-criteria decision-making algorithm unit and a fuzzy evaluation algorithm unit, used to realize the calculation of evaluation index weights, multi-dimensional data quantitative analysis and adaptation score generation; Assessment report generation module: used to identify adaptability shortcomings, generate structured assessment reports, and support personalized configuration of report content and export in multiple formats; Intelligent Linkage Recommendation Module: Equipped with an intelligent recommendation engine, it establishes data interaction with a customized training resource library to achieve precise delivery and dynamic adjustment of targeted training content; Model Iteration and Optimization Module: Used to collect various types of data required for iterative updates, and to calibrate the weights of evaluation indicators, update evaluation rules, and optimize the parameters of the evaluation model.

9. The VR training operation process adaptability assessment device for power operations according to claim 8, characterized in that, The multi-source data acquisition module establishes a connection with VR interactive devices, motion capture systems, and physiological sensing devices through an industrial-grade communication interface, supporting adaptation to multiple industrial communication protocols such as RS485, RSCAN, and Ethernet. The dynamic evaluation calculation module uses a high-performance processing chip, which supports parallel computing and real-time evaluation, with an evaluation calculation latency of ≤1s. The intelligent linkage recommendation module establishes a linkage interface with the smart training management platform and the VR training equipment management system to realize one-click push of training content and feedback of training effect data.

Images