Student data analysis method and system for inspection training of electric power communication machine room

Abstract

The invention discloses a trainee data analysis method and system for electric power communication machine room inspection training, and relates to the technical field of electric power communication machine room inspection, and the method comprises the steps: collecting the user basic information of trainees; preprocessing the basic information of the user, concrete the data by using a label, and counting and distinguishing user groups; capturing dynamic changes of trainee features, perfecting and modifying labels, and establishing a dynamic model of trainee portraits; and according to the dynamically changing student demands, a demand prediction model is established, the potential demands of the students are predicted, and personalized training is provided. Aiming at a multi-dimensional index evaluation system in the field of electric power communication machine room inspection, the skill evaluation grade of the student is set, the inspection skill proficiency of the student is quickly mastered through the evaluation result, and the training work in the field of electric power communication machine room inspection training is assisted.

Description

Technical Field

[0001] The present invention relates to the technical field of power communication room inspection, and more particularly to a trainee data analysis method and system for power communication room inspection training. Background Art

[0002] Due to the limitations of power system operation safety, economy and other factors, it is impossible to set up line breakage, pipe disconnection and other faults in the actual engineering scene of the power communication room for trainees to conduct inspections. However, training that is divorced from the actual engineering is not conducive to trainees' understanding of sudden accident phenomena and their familiarity with the room environment. By using a virtual simulation training system to simulate the actual power communication room, trainees can complete the daily inspection work of the power communication room in a 3D scene, which is of great help to improve the professional skills of trainees.

[0003] The current training system is out of touch with theory and practice, lacks interest, and cannot meet the personalized learning needs of trainees. In addition, the current training courses are limited in interactivity, and the interaction between trainees and teachers and between trainees is relatively limited, which limits the participation and learning experience of trainees. In addition, the update speed of traditional courses may be slow, resulting in a certain lag between the course content and the latest developments. New teaching methods and means need to be continuously integrated to improve the interactivity and learning experience of trainees.

[0004] Therefore, how to provide a student data analysis method and system for power communication room inspection training, set the student's skill evaluation level for the multi-dimensional indicator evaluation system in the field of power communication room inspection, and quickly grasp the student's inspection skill proficiency through the evaluation results to assist the training work in the field of power communication room inspection training is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0005] In view of this, the present invention provides a trainee data analysis method and system for power communication room inspection training, which draws a detailed user portrait by deeply mining and comprehensively analyzing the multi-dimensional data of the trainees' background, skill level, learning preference, etc., and lays a solid foundation for designing a training program with strong pertinence and obvious personalized characteristics. The evaluation results of the trainees are evaluated by designing an indicator evaluation system with diversified indicators, so as to intelligently adjust the difficulty and complexity of the task, ensure that the trainees are always in a moderate challenge state, effectively avoid the frustration and boredom of the trainees, and promote their continuous learning motivation and growth potential.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a method for analyzing trainee data for power communication room inspection training, comprising:

[0007] Collect basic user information of students;

[0008] Preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups;

[0009] Capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits;

[0010] And based on the dynamically changing needs of students, we establish a demand forecasting model to predict the potential needs of students and provide personalized training.

[0011] Preferably, the basic user information includes the student's attribute data, professional data and learning data.

[0012] Preferably, providing personalized training includes: determining skill evaluation indicators and calculating correlation coefficients between the skill evaluation indicators;

[0013] Obtaining power communication room inspection skill evaluation data according to the correlation coefficient, and obtaining trainee assessment results based on the power communication room inspection skill evaluation data;

[0014] The trainees' electric power communication room inspection skill evaluation level is determined based on their electric power communication room inspection skill evaluation results, and a personalized electric power communication room inspection checkpoint is generated.

[0015] Preferably, the correlation coefficient between the skill evaluation indicators is expressed as:

[0016]

[0017] In the formula, x i d i They represent the i-th sampling value of the evaluation index within the same attribute index, They represent the sampling mean values ​​of the evaluation indicators respectively, and the value range of κ is [-1,1].

[0018] Preferably, the power communication room inspection skill evaluation data is expressed as:

[0019] L=EU T ;

[0020] Among them, L represents the inspection skill evaluation value of the power communication room, E represents the standard evaluation set of the evaluation index set, and U represents the evaluation vector that meets the inspection skill evaluation matrix of the power communication room.

[0021] Preferably, the evaluation vector in the inspection skill evaluation matrix of the power communication room is calculated and expressed as:

[0022] U=WK=(u1,u2,…,u m );

[0023] Where W represents the weight set of inspection skill evaluation indicators for power communication room, and K represents the training effect evaluation vector set.

[0024] Preferably, the trainee's power communication room inspection skill evaluation levels include: no inspection skill, low inspection skill, medium inspection skill, high inspection skill and perfect inspection skill.

[0025] Preferably, generating a personalized power communication room inspection checkpoint includes:

[0026] When a student's skill evaluation level for a certain inspection content is no inspection skill, the error penalty for this inspection content will be removed during level design, and a corresponding prompt tool will be added. At the same time, the detection points for this inspection content will be increased, so that students without basic skills can learn this content.

[0027] When a trainee's skill evaluation result for a certain inspection content is low, the level design will reduce the error penalty for that inspection content and increase the detection points for that inspection content to enhance the trainee's practical experience;

[0028] When a student's skill evaluation result for a certain inspection content is medium inspection skill, the difficulty of the level will not change at all, so as to retain the current challenge difficulty;

[0029] When a student's skill evaluation result for a certain inspection content is high, the error penalty for that inspection content will be increased during level design to increase the challenge difficulty of the level;

[0030] When a student's skill evaluation result for a certain inspection content is perfect inspection skills, the level design will remove the inspection points of this inspection content and add inspection points for other items. While affirming the student's proficiency in this inspection skill, the skill mastery of other inspection items will be enhanced.

[0031] Preferably, a trainee data analysis system for power communication room inspection training includes:

[0032] Information collection module, used to collect basic user information of students;

[0033] A preprocessing module is used to preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups;

[0034] The initial portrait model building module is used to capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits;

[0035] The personalized training module is used to establish a demand forecasting model based on the dynamically changing needs of trainees, predict the potential needs of trainees, and provide personalized training.

[0036] Preferably, the personalized training module includes: a correlation coefficient calculation unit, a power communication room inspection skill evaluation unit, and a personalized inspection level generation unit;

[0037] The correlation coefficient calculation unit is used to determine the skill evaluation index and calculate the correlation coefficient between the skill evaluation indexes;

[0038] The electric power communication room inspection skill evaluation unit is used to obtain the electric power communication room inspection skill evaluation data according to the correlation coefficient, and obtain the trainee assessment evaluation result based on the electric power communication room inspection skill evaluation data;

[0039] The personalized inspection level generation unit is used to determine the trainee's power communication room inspection skill evaluation level according to the trainee's power communication room inspection skill evaluation result, and generate a personalized power communication room inspection level.

[0040] Through the above technical solutions, it can be known that compared with the prior art, the present invention discloses a method and system for analyzing trainee data for power communication room inspection training, including: collecting basic user information of trainees; preprocessing the basic user information, using labels to visualize the data, and statistically distinguishing user groups; capturing the dynamic changes of trainee characteristics, improving and modifying labels, and establishing a dynamic model of trainee portraits; and according to the dynamically changing needs of trainees, establishing a demand prediction model, predicting the potential needs of trainees, and providing personalized training. The present invention draws a meticulous user portrait by deeply mining and comprehensively analyzing multi-dimensional data such as the background, skill level, and learning preferences of trainees, laying a solid foundation for designing targeted and personalized training programs. By designing an indicator evaluation system with diversified indicators to evaluate the assessment results of trainees, the difficulty and complexity of the task can be intelligently adjusted to ensure that trainees are always in a moderate state of challenge, effectively avoiding the frustration and boredom of trainees, and promoting their continuous learning motivation and growth potential. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0042] Figure 1 A flow chart of a method for analyzing trainee data for power communication room inspection training provided by the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The embodiment of the present invention discloses a method for analyzing trainee data for power communication room inspection training, such as Figure 1 As shown, including:

[0045] Collect basic user information of students;

[0046] Preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups;

[0047] Capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits;

[0048] And based on the dynamically changing needs of students, we establish a demand forecasting model to predict the potential needs of students and provide personalized training.

[0049] Specifically, the basic user information includes the student's attribute data, professional data and learning data.

[0050] In a specific embodiment of the present invention, the user portrait is a user model based on user data, which can vividly and accurately outline the model of the trainee's knowledge background, skill level, learning preference, etc. The embodiment of the present invention first collects the user data of the trainee user, including: 1) attribute data: the attribute data of the trainee includes the trainee's name, gender, age, education and major. Such data remains basically stable in the long term and is easy to obtain. It belongs to the basic data in the user data; 2) professional data: the professional data of the trainee includes the user's historical position, historical work records, scientific research results, grades or qualification certificates. Such data changes greatly and is difficult to obtain. It requires the user to actively supplement it many times. It is the key data for outlining the user portrait; 3) learning data: the trainee's learning data includes the trainee's historical training data. The acquisition difficulty of such data is relatively low and the change is not large. It is the key data that affects the subsequent adaptive training. The above data can all be obtained in the form of questionnaires.

[0051] The user basic information is preprocessed, including: cleaning, processing, mining and analyzing the collected raw data to form high-quality standard data and weave it into a network, laying the foundation for subsequent result evaluation and adaptive training.

[0052] Use labels to visualize data and statistically distinguish user groups, including: classify and process data according to indicators such as data type, usage scenario, and application goal through natural language processing, text mining, machine learning and other technologies; then, statistically analyze and process abstract user-related data to restore it into more instructive, more vivid, and easier to understand information, explore the correlation between data, use labels to visualize data, and statistically distinguish user groups;

[0053] The collected raw data is fused with multi-source information to lay the foundation for subsequent result evaluation and adaptive training. The embodiment of the present invention adopts the DS evidence fusion method to comprehensively analyze the raw data and output the initial student portrait model. The specific process is as follows:

[0054] Take U={u1,u2......u n} represents the framework of the initial student portrait model, in which any element is independent and mutually exclusive, and all elements can be combined into a set, which can be defined as the power set of U. U If m:2 U →[0,1], then the following two requirements are met at the same time:

[0055] (1) For the impossible occurrence, the probability is 0, which can be represented by m(Φ) = 0;

[0056] (2) The sum of all possible probabilities is set to 1, which can be obtained by express.

[0057] The basic probability distribution of proposition Y on U is defined as m, which can also be defined as a mass function. The trust of Y can be expressed as m(Y):

[0058]

[0059] definition Where p(Y) represents the likelihood function of Y.

[0060] exist Under the condition of , the evidence synthesis process of elements on U can be expressed by the following formula:

[0061]

[0062] In the formula, C represents the conflict coefficient, and its calculation formula is as follows:

[0063]

[0064] The C value can be used to describe the level of conflict between evidence. The larger the value, the more significant the conflict between different evidences. The smaller the C value, the higher the credibility of the evidence. This results in better information fusion results and more accurate initial student portrait model.

[0065] Based on the initial student portrait model, the dynamic changes of student characteristics are captured, labels are improved and modified, and a dynamic model of student portrait is established, including: incorporating an information feedback mechanism to timely capture the dynamic changes of user characteristics, updating the user portrait database, improving and modifying labels, and establishing a dynamic model of user portrait. The database establishes a demand prediction model based on dynamically changing user needs, predicts the user's future potential needs, and then provides accurate adaptive targeted training; finally, the user portrait label system is presented as a role attribute on the user interface with vivid, figurative, and intuitive visual symbols using visualization technology, so that users can see their own characteristics and preferences at a glance, and users can also object to inaccurate labels and re-examine them.

[0066] The embodiment of the present invention draws a detailed user portrait by deeply mining and comprehensively analyzing the multi-dimensional data of the trainees, such as their background, skill level, and learning preferences, laying a solid foundation for designing a targeted and personalized training program. The evaluation system of diversified indicators is designed to evaluate the assessment results of the trainees, so as to intelligently adjust the difficulty and complexity of the tasks, ensure that the trainees are always in a moderate state of challenge, effectively avoid the frustration and boredom of the trainees, and promote their continuous learning motivation and growth potential.

[0067] Specifically, personalized training is provided, including: determining skill evaluation indicators and calculating the correlation coefficients between the skill evaluation indicators;

[0068] Obtaining power communication room inspection skill evaluation data according to the correlation coefficient, and obtaining trainee assessment results based on the power communication room inspection skill evaluation data;

[0069] The trainees' electric power communication room inspection skill evaluation level is determined based on their electric power communication room inspection skill evaluation results, and a personalized electric power communication room inspection checkpoint is generated.

[0070] In a specific embodiment of the present invention, the construction process of the power communication room inspection skill evaluation system includes: first, setting the trainee's power communication room inspection skill evaluation level, generating an evaluation set V = {v1, v2, v3, v4, v5}, where different elements represent no inspection skills, low inspection skills, medium inspection skills, high inspection skills, and perfect inspection skills, respectively, and dividing the inspection skill evaluation limit into five levels, using the monitoring threshold and speed change rate dual control indicators for real-time control, as shown in Table 1.

[0071] Table 1 Skill evaluation criteria

[0072]

[0073]

[0074] Among them, l represents the preset monitoring value skill evaluation limit, v represents the speed change rate skill evaluation limit, and some skill evaluation index limits include upper and lower limits. The evaluation results obtained under the condition of medium state are the best for this type of skill evaluation index value, so this type of evaluation index is defined as moderate skill evaluation index; the remaining skill evaluation indexes only have a single limit value, and the value of this type of skill evaluation index is inversely proportional to the evaluation result, so this type of index is defined as a negative index. The value that describes the fluctuation between two adjacent monitoring data in a unit time is the speed change rate.

[0075] After that, the indicator system is constructed. Let P represent the number of initial evaluation indicators, and the correlation values ​​between the indicators are extremely close. After classifying the P initial evaluation indicators, the indicator matrix is ​​constructed:

[0076]

[0077] In the formula, m represents the number of initial evaluation index categories, N represents the category attribute, and the subscript numbers represent the first category, the second category, and the mth category respectively.

[0078] Let κ represent the correlation coefficient between indicators and construct the indicator correlation matrix:

[0079] Specifically, the correlation coefficient between the skill evaluation indicators is expressed as:

[0080]

[0081] In the formula, x i d i They represent the i-th sampling value of the evaluation index within the same attribute index, They represent the sampling average of the evaluation indexes respectively. The value range of κ is [-1,1]. When its value is a positive number, it means that the two evaluation indexes are positively correlated, otherwise it is a negative correlation. When the absolute value of κ is 1, it means that the two evaluation indexes are completely correlated. When the absolute value is 0, it means that the two evaluation indexes are independent of each other. The calculation formula for the sampling average of the evaluation index is as follows:

[0082]

[0083] In the formula, n represents the number of sampling points. The correlation coefficient values ​​between the two evaluation indicators are obtained, and after sorting the correlation coefficient values, the evaluation indicator correlation matrix is ​​obtained.

[0084] In the evaluation index correlation matrix, one of the two indicators with correlation coefficient values ​​higher than 0.82 is deleted, and the average indicators with correlation coefficient values ​​between 0.45 and 0.82 and more than 2 are deleted. Then, the simplified power communication room inspection skill evaluation index is obtained. After normalization of the evaluation index, the power communication room inspection skill evaluation system is obtained.

[0085] Specifically, the power communication room inspection skill evaluation data is expressed as:

[0086] L=EU T (8)

[0087] Among them, L represents the inspection skill evaluation value of the power communication room, E represents the standard evaluation set of the evaluation index set, and U represents the evaluation vector that meets the inspection skill evaluation matrix of the power communication room.

[0088] In a specific embodiment of the present invention, the specific process of student assessment result evaluation and level adaptive matching includes: first, let C = {c1, c2, ..., c n} represents the set of evaluation indicators for inspection skills in power communication room, and the score corresponding to the set is expressed in vector form. Then the standard evaluation set of the evaluation indicator set can be E = {e1, e2, …, e n}express.

[0089] According to the inspection skill evaluation index set of the power communication room, the inspection skill evaluation matrix X of the power communication room is established. ij ,make Represents the dimension value of the matrix labeled t:

[0090]

[0091] Calculate the inspection skill evaluation matrix X of the power communication room ij The evaluation vector of:

[0092] K i =ω i R i (k i1 ,k i2 ,…,k in ) (10)

[0093] In the formula, and i = 1, 2, ..., n, j = 1, 2, ..., k, t = 1, 2, ..., m, K i represents the i-th evaluation vector of the fuzzy matrix, and ω represents the weight value of the evaluation vector.

[0094] Specifically, the evaluation vector in the inspection skill evaluation matrix of the power communication room is calculated, and the vector is represented by U:

[0095] U=WK=(u1,u2,…,u m ) (11)

[0096] Where W represents the weight set of inspection skill evaluation indicators in the power communication room, K represents the training effect evaluation vector set, and u t The expression formula is as follows:

[0097]

[0098] When u t When the value is not equal to 1, normalize formula (12) to obtain:

[0099]

[0100] The standardized matrix of the inspection skill evaluation vector of the power communication room is obtained by formula (13):

[0101] U′=(u1′,u′2,…,u′ m ) (14)

[0102] After the above steps, the inspection skill evaluation data of the power communication room is calculated:

[0103] L=EU T (15)

[0104] Wherein, L represents the electric power communication room inspection skills evaluation data, and the evaluation results of the trainees' electric power communication room inspection skills can be obtained based on the evaluation data.

[0105] Specifically, the trainees' power communication room inspection skill evaluation levels include: no inspection skill, low inspection skill, medium inspection skill, high inspection skill and perfect inspection skill.

[0106] Specifically, based on the trainees' power communication room inspection skill evaluation results, personalized power communication room inspection checkpoints are generated, including:

[0107] When a student's skill evaluation level for a certain inspection content is no inspection skill, the error penalty for this inspection content will be removed during level design, and a corresponding prompt tool will be added. At the same time, the detection points for this inspection content will be increased, so that students without basic skills can learn this content.

[0108] When a trainee's skill evaluation result for a certain inspection content is low, the level design will reduce the error penalty for that inspection content and increase the detection points for that inspection content to enhance the trainee's practical experience;

[0109] When a student's skill evaluation result for a certain inspection content is medium inspection skill, the difficulty of the level will not change at all, so as to retain the current challenge difficulty;

[0110] When a student's skill evaluation result for a certain inspection content is high, the error penalty for that inspection content will be increased during level design to increase the challenge difficulty of the level;

[0111] When a student's skill evaluation result for a certain inspection content is perfect inspection skills, the level design will remove the inspection points of this inspection content and add inspection points for other items. While affirming the student's proficiency in this inspection skill, the skill mastery of other inspection items will be enhanced.

[0112] In a specific embodiment of the present invention, a trainee data analysis system for power communication room inspection training includes:

[0113] Information collection module, used to collect basic user information of students;

[0114] A preprocessing module is used to preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups;

[0115] The initial portrait model building module is used to capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits;

[0116] The personalized training module is used to establish a demand forecasting model based on the dynamically changing needs of trainees, predict the potential needs of trainees, and provide personalized training.

[0117] Specifically, the personalized training module includes: a correlation coefficient calculation unit, a power communication room inspection skill evaluation unit, and a personalized inspection level generation unit;

[0118] The correlation coefficient calculation unit is used to determine the skill evaluation index and calculate the correlation coefficient between the skill evaluation indexes;

[0119] The electric power communication room inspection skill evaluation unit is used to obtain the electric power communication room inspection skill evaluation data according to the correlation coefficient, and obtain the trainee assessment evaluation result based on the electric power communication room inspection skill evaluation data;

[0120] The personalized inspection level generation unit is used to determine the trainee's power communication room inspection skill evaluation level according to the trainee's power communication room inspection skill evaluation result, and generate a personalized power communication room inspection level.

[0121] The embodiment of the present invention establishes a multi-dimensional indicator evaluation system for the field of power communication room inspection, and sets the skill evaluation level of trainees, so that trainees can quickly master their own inspection skill proficiency through the evaluation results. The embodiment of the present invention also designs the evaluation method of trainee assessment results and the personalized level setting method, which can accurately portray the skill level of trainees, increase learning opportunities for trainees' weaknesses, and increase challenge opportunities for trainees' strengths, so as to assist the training work in the field of power communication room inspection training.

[0122] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0123] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing trainee data for power communication room inspection training, characterized in that: include: Collect basic user information of students; Preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups; Capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits; And based on the dynamically changing needs of students, we establish a demand forecasting model to predict the potential needs of students and provide personalized training.

2. According to claim 1, a method for analyzing trainee data for power communication room inspection training is characterized in that: The user basic information includes the student's attribute data, professional data and learning data.

3. According to claim 1, a method for analyzing trainee data for power communication room inspection training is characterized in that: Provide personalized training, including: determine skill evaluation indicators and calculate the correlation coefficients between each skill evaluation indicator; Obtaining power communication room inspection skill evaluation data according to the correlation coefficient, and obtaining trainee assessment results based on the power communication room inspection skill evaluation data; The trainees' electric power communication room inspection skill evaluation level is determined based on their electric power communication room inspection skill evaluation results, and a personalized electric power communication room inspection checkpoint is generated.

4. The method for analyzing trainee data for power communication room inspection training according to claim 3 is characterized in that: The correlation coefficient between the skill evaluation indicators is expressed as: In the formula, x i d i They represent the i-th sampling value of the evaluation index within the same attribute index, They represent the sampling mean values ​​of the evaluation indicators respectively, and the value range of κ is [-1,1].

5. The method for analyzing trainee data for power communication room inspection training according to claim 3 is characterized in that: The power communication room inspection skill evaluation data is expressed as: THE EU T ; Among them, L represents the inspection skill evaluation value of the power communication room, E represents the standard evaluation set of the evaluation index set, and U represents the evaluation vector that meets the inspection skill evaluation matrix of the power communication room.

6. The method for analyzing trainee data for power communication room inspection training according to claim 5 is characterized in that: Calculate the evaluation vector in the inspection skill evaluation matrix of the power communication room, expressed as U: U=WK=(u1,u2,…,u m ); Where W represents the weight set of inspection skill evaluation indicators for power communication room, and K represents the training effect evaluation vector set.

7. The method for analyzing trainee data for power communication room inspection training according to claim 3 is characterized in that: The trainees' power communication room inspection skill evaluation levels include: no inspection skills, low inspection skills, medium inspection skills, high inspection skills and perfect inspection skills.

8. The method for analyzing trainee data for power communication room inspection training according to claim 7, characterized in that: Generate personalized power communication room inspection checkpoints, including: When a student's skill evaluation level for a certain inspection content is "no inspection skill", the level design will remove the error penalty for this inspection content, add corresponding prompt tools, and increase the detection points for this inspection content; When a student's skill evaluation result for a certain inspection content is low, the error penalty for this inspection content will be reduced during level design, and at the same time, the detection points for this inspection content will be increased; When a student's skill evaluation result for a certain inspection content is medium inspection skill, the difficulty of the level will not change; When a student's skill evaluation result for a certain inspection content is high, the error penalty for that inspection content will be increased during level design; When a student's skill evaluation result for a certain inspection content is perfect inspection skill, the inspection points of this inspection content will be removed during level design, and inspection points for other items will be added.

9. A trainee data analysis system for power communication room inspection training, characterized in that: include: Information collection module, used to collect basic user information of students; A preprocessing module is used to preprocess the basic information of the user, visualize the data using tags, and statistically distinguish user groups; The initial portrait model building module is used to capture the dynamic changes of student characteristics, improve and modify labels, and build a dynamic model of student portraits; The personalized training module is used to establish a demand forecasting model based on the dynamically changing needs of trainees, predict the potential needs of trainees, and provide personalized training.

10. A trainee data analysis system for power communication room inspection training according to claim 9, characterized in that: The personalized training module includes: a correlation coefficient calculation unit, a power communication room inspection skill evaluation unit, and a personalized inspection level generation unit; The correlation coefficient calculation unit is used to determine the skill evaluation index and calculate the correlation coefficient between the skill evaluation indexes; The electric power communication room inspection skill evaluation unit is used to obtain the electric power communication room inspection skill evaluation data according to the correlation coefficient, and obtain the trainee assessment evaluation result based on the electric power communication room inspection skill evaluation data; The personalized inspection level generation unit is used to determine the trainee's power communication room inspection skill evaluation level according to the trainee's power communication room inspection skill evaluation result, and generate a personalized power communication room inspection level.

Images