User skill portraying method and system for electric power simulation training

Abstract

The invention discloses a user skill portraying method and system for electric power simulation training. According to the method, user operation behaviors in electric power simulation training are comprehensively collected and analyzed, a multi-dimensional user portrait is generated, dynamic scoring is performed according to actual performance of a user, and finally comprehensive evaluation of user operation capability and skill portrait display are realized. According to the scheme of the invention, more efficient, accurate and fair user evaluation is provided.

Description

Technical Field

[0001] This invention belongs to the field of power systems, and specifically relates to a user skills profiling method and system for power simulation training. Background Technology

[0002] In existing power system simulation training, simulation systems are mainly used to simulate the operation procedures and fault diagnosis of power equipment. However, the systems lack sufficient scientific rigor and accuracy in recording trainees' behavior and assessing their comprehensive abilities. Most existing simulation systems can only record basic operational data, such as user login duration and task completion status, lacking multi-dimensional comprehensive evaluation methods. Especially in generating user skill profiles, existing systems almost entirely fail to provide dynamic, multi-dimensional profile generation methods, limiting the accuracy and effectiveness of the assessment. Furthermore, existing technologies cannot effectively assess users' true performance capabilities during operation, especially for long-term system users, whose performance evaluation lacks timeliness. The excessive weighting of historical data fails to reflect recent improvements or declines in operational performance in a timely manner. Evaluation methods are too fixed, failing to dynamically adjust scores based on users' operating habits and behavioral patterns, thus unable to flexibly reflect changes in user capabilities and struggle to cope with the diversity of user behavior. When a large amount of user operational data accumulates, the system struggles to effectively balance historical data with recent performance. Over-reliance on historical data may mask recent skill improvements, while completely ignoring historical data fails to comprehensively assess long-term performance. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a user skills profiling method and system for power simulation training, thereby resolving the technical problem of inaccurate scoring due to data redundancy.

[0004] To solve the above-mentioned technical problems, the present invention adopts the following technical solution.

[0005] This invention first discloses a user skills profiling method for power simulation training, the method comprising the following steps: The system collects user operation data from multiple dimensions during power simulation training, extracts and transforms the collected operation data to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data, and stores the above data in a time series database. A user profile is generated based on the operation data, and the user level of the current user is determined. The user level includes a first user level, a second user level, and a third user level. If the current user's user level is Level 1, the user's operation is scored based on the preset initial baseline value. If the current user's user level is Level 2, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is Level 3, the user's operation is scored based on the scrolling window and data decay mechanism, and the score result is output.

[0006] The present invention further includes the following preferred embodiments: The login frequency data includes the number of times a user logs in daily, weekly, and monthly; the online time data records the online time a user spends during each login session; the practice time data records the actual operation time a user spends in each task; the task completion status includes the number of tasks, the accuracy of completion, and the efficiency; the error rate data includes misoperations, redundant operations, incorrect sequences, and omitted operations; the operation evaluation data scores the user based on their performance during training, and the evaluation criteria include the correctness of the operation, the fluency, and the efficiency of task completion.

[0007] The step of storing the aforementioned data in a time-series database further includes: classifying and storing user operation behavior data in a hierarchical manner according to data type; storing basic data in a basic database and storing key data in a high-performance database.

[0008] The basic data includes login frequency data and online duration data, while the key data includes task completion data and error rate data.

[0009] If the current user's user level is the second user level, then the user's operation is scored based on the task completion data, practice time data, and error rate data, further including: Based on task completion status S 任务完成情况 Practice duration S 练习时长 and error rate S 错误率 Rate advanced users:

[0010] Wherein, β1, β2, and β3 represent the weights of task completion, practice time, and error rate, respectively.

[0011] If the current user's user level is the third user level, then the user's user actions are scored based on a scrolling window and data decay mechanism, further including: Based on data from the last n months, S 最近n个月的数据 Rate advanced users:

[0012] Where n is the number of months, ω i Let be the data weight for the i-th month.

[0013] The data weight ω for the i-th month i The calculation is as follows:

[0014] α is the attenuation coefficient, ω i W is the weight for the i-th month. i These are the normalized weights.

[0015] This invention also discloses a user skill profiling system for power simulation training that utilizes the aforementioned user skill profiling method for power simulation training, comprising: The operation data acquisition module is used to collect operation data from users in multiple dimensions during power simulation training. The collected operation data is extracted and transformed to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data. The above data are stored in the time series database. The user rating module is used to generate a user profile based on the operation data and determine the current user's user level, which includes a first user level, a second user level, and a third user level. If the current user's user level is Level 1, the user's operation is scored based on the preset initial baseline value. If the current user's user level is Level 2, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is Level 3, the user's operation is scored based on the scrolling window and data decay mechanism, and the score result is output.

[0016] Accordingly, this application also discloses a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the aforementioned user skill profiling method for power simulation training.

[0017] Accordingly, this application also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned user skill profiling method for power simulation training.

[0018] The beneficial effects of this invention are as follows: Compared with existing technologies, this invention provides a user skill profiling method and system for power simulation training. By introducing a rolling window and a data decay algorithm, it achieves dynamic scoring of user operation data, ensuring that recent data has a higher weight and historical data gradually fades. In practical applications, this mechanism can reflect the user's latest operational performance in real time, avoiding excessive influence of historical data on the scoring, making the scoring more in line with the user's current ability. Based on six operational dimensions, a multi-dimensional user profile is automatically generated, comprehensively reflecting the user's operational capabilities. Visual methods such as radar charts are used to display the user's strengths and weaknesses, helping administrators intuitively grasp the user's ability level and helping managers optimize training programs in a targeted manner. It more comprehensively and intuitively displays the user's strengths and weaknesses, improving the accuracy and effectiveness of training. The weights of each dimension are dynamically adjusted through automated algorithms, without manual intervention, ensuring that the scoring reflects the user's operational performance in real time. In practical applications, this mechanism avoids errors from manual adjustments, making the scoring more reasonable and dynamically adapting to changes in user operations, effectively improving the scientific nature and accuracy of the scoring. Based on the user's operational performance, users are divided into beginner, intermediate, and advanced levels, with different scoring standards set for different levels. The user tiered system effectively avoids inaccurate scoring due to insufficient initial data. Furthermore, the scores for advanced users dynamically reflect their performance, preventing data distortion and ensuring that their scores accurately reflect their true skill level, thus enhancing fairness and flexibility. Personalized training suggestions are automatically generated based on user performance, and administrators can provide feedback and optimization on the suggestions' effectiveness. In practical applications, personalized training suggestions help users quickly improve their weaknesses. Administrator feedback allows the system to continuously optimize training plans, making the suggestions increasingly accurate and effective. This dynamic optimization of training content allows suggestions to be adjusted as user capabilities change, improving the accuracy and effectiveness of training programs and ultimately promoting rapid improvement in user skills. Attached Figure Description

[0019] Figure 1 This is a flowchart of the user skill profiling method for power simulation training in this invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0021] The embodiments described in this application are merely some, not all, embodiments of the present invention. Based on the spirit of the present invention, all other embodiments obtained by those skilled in the art without inventive effort are within the protection scope of the present invention.

[0022] To address the shortcomings of existing technologies, this invention proposes a user skill profiling method and system for power simulation training, applicable to simulation environments for operation training of primary and secondary systems in power grids and substations. The core of this method lies in the comprehensive integration and analysis of user operational behavior data within the simulation environment to generate multi-dimensional user profiles. A rolling window and data decay mechanism are introduced to achieve dynamic scoring based on actual user performance. This method dynamically adjusts evaluation weights according to changes in user operational skills, considering both recent performance and historical data to ensure that the scoring results accurately reflect the user's current operational capabilities, ultimately achieving a comprehensive assessment and profiling of the user's operational skills.

[0023] See Figure 1 As shown, this method achieves its goal by constructing a system based on existing data and focusing on data integration and evaluation. Specifically, it includes the following two core steps: Step 1: Collect user operation data from multiple dimensions during power simulation training. Extract and transform the collected operation data to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data. Store the above data in a time-series database.

[0024] As the data foundation layer of the method, its core task is to extract scattered user operation data from multiple existing business database tables of the power simulation training platform and convert it into a unified format suitable for analysis for storage.

[0025] Through a predetermined data extraction process, raw records related to user behavior are periodically extracted from original data sources such as the simulation platform's operation log table, user information table, and task record table. This raw data is scattered and heterogeneous; this invention systematically maps it to six core dimensions defined for user profiling analysis: Login frequency data: Extract login / logout timestamps from the user session log table and calculate the number of logins per day, week, and month.

[0026] Online time data: Based on session records and the last operation timestamp, the effective online time for each login is calculated, and invalid idle sessions are filtered out.

[0027] Practice duration data: Extract the start and end times of tasks from the task execution record table, and calculate the actual operation time for each task.

[0028] Task completion status data: By integrating task records and operation step records, and comparing the actual operation sequence with the standard answer sequence, the system automatically calculates the accuracy (step correctness rate) and efficiency (relative to standard time) of task completion.

[0029] Error rate data: From the error log or operation audit table, erroneous operations are categorized and statistically analyzed (such as misoperation, incorrect sequence, etc.), and their frequency and overall error rate are calculated.

[0030] Operational evaluation data: Users are scored based on their performance during training, with evaluation criteria including the correctness, fluency, and efficiency of task completion. This performance evaluation, combined with the scoring mechanism, provides a reference for subsequent user profile generation and competency assessment.

[0031] After data collection is complete, the operational behavior data is stored in the database. To ensure data traceability and reliability, a time-series database is used to store user operational behavior data in chronological order, and an independent data record table is created for each user. The specific storage strategy is as follows: User behavior data is categorized and stored in a hierarchical manner based on its data type. Cumulative data with long statistical periods, such as login frequency, online time, and practice time, are stored in a basic database suitable for large-capacity storage and batch analysis. Data closely related to real-time performance evaluation and immediate feedback, such as task completion status, error rate, and operation evaluation, which are frequently accessed and queried, are stored in a high-performance database. The advantage of hierarchical storage is improved data query efficiency, especially when performing multi-dimensional analysis, enabling rapid extraction and aggregation of historical user data.

[0032] Historical data older than a certain period (e.g., 3 years) should be archived periodically to ensure that system efficiency does not decrease due to historical data redundancy. Archived data can still be used for subsequent in-depth analysis and long-term trend assessment.

[0033] Data acquisition and storage are performed in real time, ensuring real-time tracking and analysis of user behavior and adapting to the dynamically changing operational needs in power simulation training. Through hierarchical storage and multi-dimensional correlation analysis, the correlation data between different operational dimensions can be quickly queried, processed, and analyzed, thereby better generating multi-dimensional user profiles.

[0034] Step 2: Generate a user profile based on the operation data and determine the current user's user level. The user level includes a first user level, a second user level, and a third user level. If the current user's user level is the first user level, the user's operation is scored based on a preset initial baseline value. If the current user's user level is the second user level, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is the third user level, the user's operation is scored based on a scrolling window and data decay mechanism, and the scoring result is output. This step enables the generation of scores and profiles based on user classification and dynamic weighting. According to the data characteristics of different users, a differentiated scoring model is applied to ensure that the assessment results can accurately reflect their current skill level.

[0035] To assess and improve user operational capabilities, this invention introduces a user tiered evaluation mechanism. Based on user operational data and the amount and stability of data accumulated in the time-series database (such as total number of operations and usage duration), users are divided into three levels: First-level user (new user): Users who lack sufficient data accumulation and find it difficult to conduct trend analysis.

[0036] Second-level user (advanced user): Users who have accumulated stable operational data and are in the growth stage.

[0037] Third user level (advanced user): Mature users who have used the service for a long time, have a wealth of data, and whose recent performance changes need to be monitored.

[0038] A comprehensive score is given based on multi-dimensional data, with different weightings assigned to users at different levels.

[0039] For novice users, whose operational data is sparse and cannot be effectively weighted statistically, the system adopts a relative scoring method based on the initial baseline value. The core of this method is to provide novice users with a gentle and encouraging starting point, avoiding discouragement due to low scores caused by initial unfamiliarity with operations.

[0040] Initial baseline setting: The initial baseline value is derived from two aspects: first, based on the average performance data of all new users in the same historical period; and second, the qualification standard value set by domain experts according to the training objectives. This baseline value reflects the basic level that a "qualified new user" should reach.

[0041] A novice's performance on their first task is compared to an initial baseline value to calculate their relative score. The scoring formula is as follows: S 新手 = S 初始基线 * (1 + K * (S本次任务 - S 初始基线 ) / S 初始基线 ) Among them, S 本次任务 This is the raw score calculated based on fundamental metrics such as the user's operational correctness and completion time for this task; S 初始基线 K is the initial baseline value, and K is a gain coefficient less than 1 (e.g., 0.5) used to smooth score changes, ensuring that the initial score does not fluctuate excessively due to small fluctuations in a single performance. This formula ensures that a beginner's starting score is near the baseline value and adjusts smoothly up or down as their performance is better or worse than the baseline.

[0042] Guidance: The system will compare the score with the baseline value and convert it into specific feedback information, such as "Your first operation is close to the beginner level, please keep it up!" or "There is still room for improvement in operation fluency, we suggest more simulation practice." This format provides novice users with clear and positive directions for improvement.

[0043] For advanced user ratings, as user data accumulates, the system gradually reduces the influence of baseline values ​​and relies more heavily on actual user performance data. Advanced user rating S 进阶 Primarily based on task completion status S 任务完成情况 Practice duration S 练习时长 and error rate S 错误率 The specific scoring formula is as follows:

[0044] Here, β1, β2, and β3 represent the weights of task completion, practice time, and error rate in the scoring, respectively, and these weights can be flexibly adjusted according to system requirements.

[0045] For advanced users who use the system frequently, a rolling window and data decay mechanism are employed to ensure that the score reflects the user's recent performance. By setting a rolling window, only data from the most recent 12 or 36 months is considered. Within the rolling window, the data decay mechanism ensures that recent data has a higher weight and past data has a lower weight. The advanced user's score S 高级 The formula is as follows:

[0046] Among them, S 最近n个月的数据 This refers to comprehensive data from the past n months (including login frequency, online time, practice time, task completion, error rate, and performance evaluation), where n is the number of months, preferably 12 or 36, and ω... i The data weight for month i is calculated using the data decay formula:

[0047] α is the attenuation coefficient, W i The weight is the normalized weight for the i-th month. This formula ensures that, over time, historical user data is gradually de-emphasized, highlighting the performance in recent months.

[0048] This formula ensures that data from the most recent 12 or 36 months is scored, with recent data receiving greater weight and historical data receiving progressively less weight. This reflects both the user's long-term performance trends and their recent operational performance.

[0049] To generate and evaluate user profiles, specific embodiments of this invention provide complete operational steps, from user login to the final generation of user profiles, covering data collection, processing, storage, analysis, and display. The detailed steps are as follows: Step 1: User Login The algorithm records the login frequency when a user logs in and generates a preliminary login record based on the user's login data. The algorithm is described as follows: Each time a user logs in, update the user's login frequency and record the number of logins per day. If a user logs in multiple times in a day, accumulate the login count.

[0050]

[0051] Verification Case: Suppose a user's login activity in a certain month is as follows: The user logged in 3 times in week 1, 4 times in week 2, 2 times in week 3, and 5 times in week 4. Therefore, the total number of logins for the month is 3 + 4 + 2 + 5 = 14 times. Assuming the month has 30 days, the user's average monthly login frequency is:

[0052] Step 2: Record online time It automatically records user online time and monitors user activity levels. The algorithm is described as follows: The system monitors user clicks or actions using event listeners, updating online time every minute.

[0053] If a user remains inactive for an extended period, the timer should be paused to prevent false online time recordings.

[0054] formula:

[0055] Verification Case: Assume a user's effective online time per day is as follows: Day 1: 2 hours; Day 2: 3 hours; Day 3: 1.5 hours; Day 4: 2.5 hours; Day 5: 4 hours. Therefore, the user's total online time is:

[0056] Step 3: Enter the simulation operation task After a user selects a simulation task, the system records the user's task completion status and practice time.

[0057] The algorithm is described as follows: The system records the start and end times of each user's task. It also updates the "Task Completion Status" metric based on the task's progress and results.

[0058]

[0059] Validation Case: Suppose a user completed the following exercises within one month: Task 1 completed: 2 hours Task 2 completed: 1 hour Task 3 completed: 1.5 hours Task 4 completed: 2 hours Total practice time is:

[0060] Assuming the user has a total of 6 tasks to complete, and actually completes 4 tasks, then the task completion rate is:

[0061] Step 4: Record user actions in real time By using event listeners and logging, every user action is recorded in real time, and categorized and marked as correct. The algorithm is described below: Each operation is compared to determine whether it meets the task requirements and is classified as either a "correct operation" or an "incorrect operation".

[0062] Errors can be categorized into redundant operations, omitted operations, misoperations, and incorrect sequences.

[0063]

[0064] Verification Case: Suppose a user performs a total of 20 operations while executing a certain task, of which 3 are erroneous operations. The error rate is:

[0065] These three erroneous operations can be categorized as follows: one redundant operation, one omitted operation, and one incorrect sequence operation.

[0066] Step 5: Generate operation evaluation and feedback Based on the user's performance in the task, an instant evaluation is generated, and a rating is provided to the user. The algorithm is described as follows: The system calculates an operational evaluation score by combining factors such as task completion rate, error rate, and practice time. The operational evaluation score ranges from 0 to 100, and the system assigns different weights to each dimension.

[0067]

[0068]

[0069] Validation Case: Assume a user's task completion rate is 66.67%, error rate is 15%, and practice time is 6.5 hours (standard practice time is 8 hours). Weights are set as follows:

[0070] The user's evaluation score was 76.92.

[0071] Operational evaluation is calculated as follows:

[0072] Step 6: Regularly collect and update user operation data User data is automatically aggregated according to daily, weekly, monthly, and yearly time periods to ensure data integrity and timeliness. The algorithm is described as follows: The scheduled task module periodically extracts user operation data from the database for archiving and updating.

[0073] The data is aggregated at different time granularities and displayed to the administrator in a graphical format.

[0074]

[0075] Verification Case: Assume the system collects user operation data monthly. The login frequencies for the past three months were 0.5, 0.6, and 0.7 respectively. The system summarizes the data as follows:

[0076] Step 7: Apply scrolling window and data decay mechanism For long-term users, a scrolling window and data decay mechanism are used to ensure the timeliness of ratings. The algorithm is described below: The rolling window length is 12 months or 36 months, and the data decay coefficient α controls the rate of weight decrease.

[0077] More recent data has a higher weight, while the weight of more distant data gradually decreases.

[0078]

[0079]

[0080] Verification Case: Assuming a rolling window of 6 months and a decay coefficient α = 0.9, the data weights for each month are as follows:

[0081] Similarly, the weight decays over time.

[0082] Step 8: Generate User Profiles Based on the user's overall operational performance, a six-dimensional user profile is generated. The algorithm is described as follows: The radar chart displays user performance across six dimensions: login frequency, online time, practice time, task completion, error rate, and operation evaluation.

[0083] Data for each dimension is displayed as a percentage, providing an intuitive view of user performance and helping administrators understand the full picture of user capabilities.

[0084] The values ​​for each dimension of the radar chart are based on the user's ratings across those dimensions and are normalized as a percentage:

[0085] For example, if a user's maximum possible score in the "Online Duration" dimension is 20 hours, and their actual online time is 15 hours, then the normalized score for this dimension would be:

[0086] Validation Case: Suppose a user's scores across six dimensions are as follows: Login frequency: 80% Online time: 75% Practice time: 65% Task completion status: 70% Error rate (reverse calculation): 85% Operational evaluation: 90% These scores are plotted on a radar chart, with each dimension's value representing the user's performance percentage in that dimension. The final user profile radar chart visually displays a user's strengths and weaknesses, providing data support for administrators' decision-making.

[0087] Step 9: Presentation and Feedback The system generates user profiles and rating results, which are displayed graphically to users and administrators, and supports real-time feedback. The algorithm is described below: The data visualization module displays user action data and ratings through dynamic charts. Administrators can analyze overall user performance and adjust training programs based on system suggestions.

[0088] User score trends are displayed using line charts and radar charts, while error rates and task completion status can be shown using bar charts.

[0089] The user's overall rating is displayed according to the trend changes on a monthly, quarterly, or yearly basis:

[0090] Verification Case: Assume a user's monthly rating is: January: 75; February: 78; March: 80; April: 82; May: 85; June: 87.

[0091] The system displays these ratings as a line graph, with the user rating curve showing an upward trend, indicating that user performance has gradually improved over the past 6 months. Administrators can use this trend data to make corresponding training adjustments and provide feedback.

[0092] The beneficial effects of this invention are as follows: Compared with existing technologies, this invention provides a user skill profiling method and system for power simulation training. By introducing a rolling window and a data decay algorithm, it achieves dynamic scoring of user operation data, ensuring that recent data has a higher weight and historical data gradually fades. In practical applications, this mechanism can reflect the user's latest operational performance in real time, avoiding excessive influence of historical data on the scoring, making the scoring more in line with the user's current ability. Based on six operational dimensions, a multi-dimensional user profile is automatically generated, comprehensively reflecting the user's operational capabilities. Visual methods such as radar charts are used to display the user's strengths and weaknesses, helping administrators intuitively grasp the user's ability level and helping managers optimize training programs in a targeted manner. It more comprehensively and intuitively displays the user's strengths and weaknesses, improving the accuracy and effectiveness of training. The weights of each dimension are dynamically adjusted through automated algorithms, without manual intervention, ensuring that the scoring reflects the user's operational performance in real time. In practical applications, this mechanism avoids errors from manual adjustments, making the scoring more reasonable and dynamically adapting to changes in user operations, effectively improving the scientific nature and accuracy of the scoring. Based on the user's operational performance, users are divided into beginner, intermediate, and advanced levels, with different scoring standards set for different levels. The user tiered system effectively avoids inaccurate scoring due to insufficient initial data. Furthermore, the scores for advanced users dynamically reflect their performance, preventing data distortion and ensuring that their scores accurately reflect their true skill level, thus enhancing fairness and flexibility. Personalized training suggestions are automatically generated based on user performance, and administrators can provide feedback and optimization on the suggestions' effectiveness. In practical applications, personalized training suggestions help users quickly improve their weaknesses. Administrator feedback allows the system to continuously optimize training plans, making the suggestions increasingly accurate and effective. This dynamic optimization of training content allows suggestions to be adjusted as user capabilities change, improving the accuracy and effectiveness of training programs and ultimately promoting rapid improvement in user skills.

[0093] This invention can be a system, method, and / or computer program product. This invention also discloses a user skills profiling system for power simulation training based on the aforementioned user skills profiling method for power simulation training, comprising: The operation data acquisition module is used to collect operation data from users in multiple dimensions during power simulation training. The collected operation data is extracted and transformed to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data. The above data are stored in the time series database. The user rating module is used to generate a user profile based on the operation data and determine the current user's user level, which includes a first user level, a second user level, and a third user level. If the current user's user level is Level 1, the user's operation is scored based on the preset initial baseline value. If the current user's user level is Level 2, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is Level 3, the user's operation is scored based on the scrolling window and data decay mechanism, and the score result is output.

[0094] Based on the spirit of this invention, those skilled in the art will readily conceive of a computer program product derived from the aforementioned user skill profiling method for power simulation training. The computer program product may include a computer-readable storage medium on which computer-readable program instructions are loaded to enable a processor to implement various aspects of this disclosure. That is, this application also includes a terminal comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to perform the steps according to the aforementioned user skill profiling method for power simulation training.

[0095] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0096] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0097] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A user skills profiling method for power simulation training, characterized in that, Includes the following steps: The system collects user operation data from multiple dimensions during power simulation training, extracts and transforms the collected operation data to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data, and stores the above data in a time series database. A user profile is generated based on the operation data, and the user level of the current user is determined. The user level includes a first user level, a second user level, and a third user level. If the current user's user level is Level 1, the user's operation is scored based on the preset initial baseline value. If the current user's user level is Level 2, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is Level 3, the user's operation is scored based on the scrolling window and data decay mechanism, and the score result is output.

2. The user skill profiling method for power simulation training according to claim 1, characterized in that, The login frequency data includes the number of times a user logs in daily, weekly, and monthly; the online time data records the online time a user spends during each login session; the practice time data records the actual operation time a user spends in each task; the task completion status includes the number of tasks, the accuracy of completion, and the efficiency; the error rate data includes misoperations, redundant operations, incorrect sequences, and omitted operations; the operation evaluation data scores the user based on their performance during training, and the evaluation criteria include the correctness of the operation, the fluency, and the efficiency of task completion.

3. The user skill profiling method for power simulation training according to claim 2, characterized in that, The step of storing the aforementioned data in a time-series database further includes: classifying and storing user operation behavior data in a hierarchical manner according to data type; storing basic data in a basic database and storing key data in a high-performance database.

4. The user skill profiling method for power simulation training according to claim 3, characterized in that, The basic data includes login frequency data and online duration data, while the key data includes task completion data and error rate data.

5. The user skill profiling method for power simulation training according to claim 4, characterized in that, If the current user's user level is the second user level, then the user's operation is scored based on the task completion data, practice time data, and error rate data, further including: Based on task completion status S 任务完成情况 Practice duration S 练习时长 and error rate S 错误率 Rate advanced users: Wherein, β1, β2, and β3 represent the weights of task completion, practice time, and error rate, respectively.

6. The user skill profiling method for power simulation training according to claim 5, characterized in that, If the current user's user level is the third user level, then the user's user actions are scored based on a scrolling window and data decay mechanism, further including: Based on data from the last n months, S 最近n个月的数据 Rate advanced users: Where n is the number of months, ω i Let be the data weight for the i-th month.

7. The user skill profiling method for power simulation training according to claim 6, characterized in that, in, The data weight ω for the i-th month i The calculation is as follows: α is the attenuation coefficient, ω i W is the weight for the i-th month. i These are the normalized weights.

8. A user skills profiling system for power simulation training, characterized in that, include: The operation data acquisition module is used to collect operation data from users in multiple dimensions during power simulation training. The collected operation data is extracted and transformed to obtain login frequency data, online duration data, practice duration data, task completion data, error rate data, and operation evaluation data. The above data are stored in the time series database. The user rating module is used to generate a user profile based on the operation data and determine the current user's user level, which includes a first user level, a second user level, and a third user level. If the current user's user level is Level 1, the user's operation is scored based on the preset initial baseline value. If the current user's user level is Level 2, the user's operation is scored based on the task completion data, practice time data, and error rate data. If the current user's user level is Level 3, the user's operation is scored based on the scrolling window and data decay mechanism, and the score result is output.

9. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the user skill profiling method for power simulation training according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the user skills profiling method for power simulation training as described in any one of claims 1-7.

Images