Education practical training intelligent management method based on big data

Abstract

The invention relates to the technical field of education practical training, and discloses an education practical training intelligent management method based on big data, and the method comprises the following key steps: setting an education practical training teaching mode, covering online and offline teaching modes to adapt to different teaching scenes, constructing a comprehensive student information database, and carrying out the intelligent management of the education practical training. The number of students, names, grades, staged test scores and teacher names are recorded, the staged test scores are used for reflecting mastering conditions of the students in all learning stages, score hierarchy evaluation is performed on the test scores, the test scores are divided into four hierarchies, and a corresponding score interval and a standard weight are set for each hierarchy. The system achieves the refined management of scores, constructs a teacher information database, quantitatively evaluates the teaching effect of teachers, formulates first and second efficiency scoring strategies, and dynamically evaluates the teaching effect and the learning effect of students.

Description

Technical Field

[0001] The present invention relates to the field of educational training technology, and in particular to an intelligent management method for educational training based on big data. Background Art

[0002] With the rise of big data technology and the continuous innovation of education models, the field of education training is facing opportunities and challenges of transformation and upgrading. The traditional education training management model relies more on experience judgment and manual operation, and has problems such as low efficiency and lack of personalization. Especially in terms of student information management, teaching effect evaluation and teaching resource allocation, it is urgent to introduce intelligent and automated solutions.

[0003] However, the existing educational training management methods have shortcomings in many aspects. For example, the collection and management of student information lacks systematization and automation, resulting in delayed information updates and difficulty in meeting rapidly changing educational needs. In addition, the evaluation of teaching effectiveness is mostly based on qualitative analysis and lacks quantitative standards and methods, which makes teaching improvement lack of scientific basis. In addition, the allocation of teaching resources often fails to fully utilize data advantages, resulting in irrational resource allocation and failure to maximize teaching effectiveness.

[0004] In view of the above problems, the present invention proposes an intelligent management method for educational training based on big data, which should have the following characteristics: by setting online and offline teaching methods, a comprehensive student information database and a teaching teacher information database are constructed, thus realizing the digitization and intelligence of educational training management. Through comprehensive analysis of information such as the number of students, names, grades, and periodic examination scores, the present invention can make a more accurate assessment of students' learning outcomes.

[0005] The present invention further realizes the quantitative tracking of students' learning progress and the multi-dimensional evaluation of teaching effect through the grade level assessment and effectiveness scoring strategy. Through the scientific calculation of the standard weights and difficulty coefficients of the grade level, the present invention can provide data support for the optimal configuration of teaching resources.

[0006] However, how to ensure the adaptability and effectiveness of this method in different educational scenarios, how to further improve the intelligent level of data processing, and how to achieve accurate matching of teaching resources are still key issues that need to be solved in this field. Therefore, developing an efficient, intelligent, and adaptable intelligent management method for educational training is of great significance for promoting the innovation of educational training models and improving the quality of education. Summary of the invention

[0007] The present invention provides an intelligent management method for educational training based on big data, which is used to promote the solution of the problems mentioned in the above background technology.

[0008] The present invention provides the following technical solution: an intelligent management method for educational training based on big data,

[0009] Optionally, setting a teaching method for educational training, wherein the teaching method includes online teaching and offline teaching;

[0010] Build a student information database;

[0011] The student information database includes the following information:

[0012] Number of students, names of students, grades of students, periodic examination scores of students and names of teachers;

[0013] The student's stage test scores are to record the student's test scores at the end of each learning stage;

[0014] The periodic examination results are divided into grades, which are recorded as grade assessment;

[0015] The grades are graded as follows:

[0016] The corresponding score range for the first grade level is [95,100] points;

[0017] The corresponding score range for the second grade is [80,95] points;

[0018] The corresponding score range for the third grade is [60,80] points;

[0019] The score range for the fourth grade is [40,60] points;

[0020] According to the grade level assessment, obtain the standard weight of each level;

[0021] Build a teacher information database;

[0022] The teaching teacher database includes the following information:

[0023] The name of the teacher, the teaching ability and effectiveness rating, and the score range available for teaching;

[0024] The teaching ability effectiveness score is a quantitative assessment of the teaching score of the teaching teacher in a specified grade range.

[0025] Optionally, the student's periodic examination results are the examination results of the student at the end of each learning stage, including:

[0026] Suppose S is the set of students' periodic examination scores, which contains the students' examination scores at the end of each learning stage, S = {s1, s2, ..., s n};

[0027] where s irepresents the score at the end of the i-th learning stage, and n is the total number of learning stages;

[0028] Set the progress score set P, P = {P1, P2, ..., P n-1};

[0029] Let P j is the progress score from the jth learning stage to the j+1th learning stage, and the calculation formula is:

[0030] P j =s j+1 -s j

[0031] P j There are three cases for the value of , namely positive, zero, and negative;

[0032] They represent whether students are making progress, not making progress, or regressing in their learning stages;

[0033] According to the grade level assessment, if P j If it corresponds to only one level score interval, the progress score of this learning stage will be implemented according to the first performance scoring strategy;

[0034] If P j Corresponding to multiple level score intervals, the improvement score of the learning stage is implemented with the second performance scoring strategy.

[0035] Furthermore, the step of obtaining the standard weights of each level according to the grade level evaluation includes:

[0036] According to the student information database, obtain the number of students, recorded as Q;

[0037] Get the number of students at the corresponding grade level at the end of the learning period, recorded as N i ,N i is the number of students in the i-th grade level;

[0038] Calculate the basic weight of each grade level, denoted as W i , W i is the basic weight of the i-th grade level, calculated by the following formula:

[0039]

[0040] Set the difficulty coefficient of the grade level, denoted as D i ,D i is the difficulty coefficient of the i-th grade level;

[0041] Get the upper limit score of the grade level, denoted as R i , R i is the upper limit score of the i-th grade level;

[0042] If it is the first achievement level, the upper limit score is 100 points;

[0043] If it is the second achievement level, the upper limit score is 95 points;

[0044] If it is the third achievement level, the upper limit score is 80 points;

[0045] If it is the fourth achievement level, the upper limit score is 60 points;

[0046] The difficulty coefficient calculation formula is:

[0047]

[0048] According to the difficulty coefficient and the basic weight, the standard weight is calculated and recorded as T i , is the standard weight of the i-th grade level, calculated by the following formula:

[0049]

[0050] Where m is the total number of grade levels.

[0051] Optionally, the above is determined based on the grade level assessment. If P j If there is only one level score interval, the progress score of the learning stage will be subject to the first performance scoring strategy, including:

[0052] According to the progress score P j , obtain the corresponding grade level standard weight;

[0053] The performance score of the corresponding grade level is calculated according to the following formula, denoted as K i :

[0054] K i =T i ×P j

[0055] Where T i It is the standard weight corresponding to the grade level.

[0056] Furthermore, if P j Corresponding to multiple level score intervals, the progress score of the learning stage is implemented with the second performance scoring strategy, including:

[0057] Get Progress Points P j For the corresponding learning stage, the test score at the end of the previous learning stage is recorded as the first score;

[0058] Get Progress Points P j The test score at the end of the corresponding learning phase is recorded as the second score;

[0059] If the level score interval of the first result does not match the level score interval of the second result, the improvement score P j The hierarchical score interval is divided into multiple sub-scores P j1 ,P j2 ,...,P jn ;

[0060] Each sub-score corresponds to a different level of achievement;

[0061] For each sub-score, execute the first performance scoring strategy and calculate the corresponding K i ;

[0062] The calculation formula is:

[0063] K i =T i ×P ji

[0064] The total performance score of each performance level is calculated based on the performance scores of different performance levels obtained according to the first performance score and the second performance score strategy.

[0065] Furthermore, according to the performance scores of different performance levels obtained by the first performance score and the second performance score strategy, the total performance score of each performance level is calculated, including:

[0066] Get the learning stage of the course taught by the teacher, recorded as the teaching stage;

[0067] According to the student information database, the test scores of students in the teaching stage are obtained;

[0068] Get the number of students in the corresponding grade level, recorded as A i , A i The number of students in each grade range corresponding to the teacher;

[0069] Calculate the total performance score for each grade level, denoted as U i , U i is the effectiveness score of the teacher corresponding to the i-th grade level;

[0070] Based on the total performance score of each grade level, the average performance score of each grade level is calculated.

[0071] Optionally, the total performance score of each grade level, and the average performance score of each grade level are calculated, including:

[0072] S1: Calculate the average performance score of each grade level, denoted as C i , the formula is:

[0073]

[0074] S2: Generate a score set based on the average performance score of the performance level, {C1, C2, ..., C n};

[0075] Sort the collection in descending order;

[0076] The sorted set is {C (1) , C (2) , ..., C (n)};

[0077] Get the average performance score C of the top three grades (1) , C (2) , C (3) ;

[0078] S3: C (1) , C (2) , C (3) The corresponding score range is marked as the teachable score range;

[0079] S4: It is recommended that teachers select students within the teaching score range for teaching;

[0080] Recommended students should select teachers to attend classes based on the score range corresponding to their test scores at the end of their most recent learning period.

[0081] The present invention has the following beneficial effects:

[0082] 1. This intelligent management method for educational training based on big data realizes the diversification of educational training teaching modes by setting online and offline teaching methods, meets the learning needs of different student groups, improves the flexibility and accessibility of teaching, and builds a student information database. The database includes key information such as the number of students, names, grades, stage test scores, and names of teachers, which provides data support for the personalized management of educational training. By recording the test scores of students at the end of each learning stage, and evaluating the score levels, the stage test scores are divided into score intervals, which can provide different Targeted teaching support and resource allocation are provided to students at different grades, thereby improving teaching effectiveness and student satisfaction. The standard weights of each grade are obtained according to the grade level assessment. This weight allocation helps to optimize the allocation of teaching resources and build an information database of teaching teachers, including the names of teaching teachers, teaching ability and effectiveness scores, and the score range that can be taught. This can quantitatively evaluate the teaching effectiveness of teachers and provide a basis for teachers' professional development and teaching improvement. By setting the teaching ability and effectiveness scores and the score range that can be taught, teacher resources are allocated to ensure that students can obtain teaching support that matches their learning stage.

[0083] 2. This intelligent management method for educational training based on big data realizes a comprehensive record and analysis of students' learning outcomes by setting a set S of students' periodic examination scores, which helps to deeply understand each student's learning progress and growth trajectory. By analyzing the positive and negative values ​​of the progress scores, the student's learning status can be identified. Positive numbers indicate progress, zero indicates a stable learning status, and negative numbers indicate a risk of regression. This evaluation mechanism helps teachers to adjust teaching methods in a timely manner. By setting a set of progress scores P, the student's progress, stability or regression can be quantitatively evaluated by calculating the changes in students' scores between adjacent learning stages, providing direct feedback for teaching adjustments. The first effectiveness scoring strategy and the second effectiveness scoring strategy are implemented. When the student's progress score corresponds to only one level score interval, the first effectiveness scoring strategy is implemented. This strategy is suitable for students with a clear learning status and a single score change. For the case where the progress score corresponds to multiple level score intervals, the second effectiveness scoring strategy is implemented. This strategy is suitable for students with large fluctuations in learning status or scores across multiple levels, which helps to analyze and guide students' learning in more detail.

[0084] 3. This intelligent management method for educational training based on big data achieves a quantitative assessment of the importance of student grades by obtaining the standard weights of each grade according to the grade level assessment. It helps to more accurately reflect the role of each grade level in educational training, set the difficulty coefficient of the grade level, adjust the weights of different grade levels, reflect the actual difficulty and teaching objectives of each level, calculate the basic weight of each grade level, ensure that the student's grade assessment is not affected by individual grade levels, and according to the standard weights of the grade levels, teachers and educational institutions can allocate teaching resources in a targeted manner.

[0085] 4. This intelligent management method for educational training based on big data, by implementing the first performance scoring strategy, evaluates the learning stage progress scores corresponding to only one level score interval, realizes the quantitative analysis of students' learning progress, improves the accuracy of students' progress evaluation, and ensures that the evaluation of progress scores matches students' actual learning outcomes by obtaining the known standard weights of the corresponding grade levels. The formula for calculating the performance score can convert students' progress scores into evaluation indicators.

[0086] 5. This intelligent management method for educational training based on big data implements the second performance scoring strategy to evaluate the progress scores across multiple grade level score intervals, thus realizing a multi-dimensional quantitative analysis of students' learning progress. When students' grades span multiple levels, the sub-scores are subdivided to evaluate students' learning performance at each level. By obtaining the first and second grades and comparing their grade level score intervals, the specific progress of students at different learning stages can be identified. For mismatched grade intervals, the progress scores are subdivided and the performance scores are calculated separately, which can reflect students' progress and learning status. By implementing the first performance scoring strategy for each sub-score, teachers can provide teaching according to students' different grade levels.

[0087] 6. The intelligent management method for educational training based on big data, in terms of calculating the total effectiveness score of each grade level, obtains the learning stage taught by the teaching teacher, that is, the teaching stage, which provides an evaluation period for the effectiveness score. Through the student information database, the test scores of students in the teaching stage can be obtained. These data are the basis for evaluating the teaching effectiveness of teachers and the learning effectiveness of students. By obtaining the number of students in the corresponding grade level, that is, the number of students in the score range corresponding to each grade level of the teaching teacher, the analysis of student groups at different grade levels is realized, thereby providing guidance and support for teaching. By calculating the total effectiveness score of each grade level, that is, the effectiveness score of the i-th grade level corresponding to the teaching teacher, a quantitative evaluation standard is provided for the teacher's teaching performance, which helps teachers understand their teaching advantages and improvement space in different grade segments.

[0088] 7. The intelligent management method for education and training based on big data realizes the evaluation of teaching effect by calculating the total efficiency score of each grade level and further obtaining the average efficiency score. In step S2, by generating a score set and sorting it, the grade level with the best teaching effect can be identified. This sorting mechanism helps education managers and teachers to quickly grasp the advantages and areas for improvement of teaching. Through step S3, the grade score interval corresponding to the average efficiency score of the top three grade levels is marked as the score interval that can be taught, which provides a clear teaching focus for the teacher, helps to concentrate resources and attention to improve the quality of teaching. In step S4, the present invention recommends that the teacher screen students for teaching in the score interval that can be taught. This strategy helps teachers to allocate teaching time and efforts more effectively, teach the student groups that are most likely to benefit, and allow students to screen teachers for lectures according to the score interval corresponding to the grade level of their own test scores at the end of the most recent learning stage. This two-way selection mechanism not only improves the accuracy of teaching matching, but also enhances students' initiative and sense of participation. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0090] 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.

[0091] Embodiment 1, optionally, setting an education training teaching method, wherein the teaching method includes online teaching and offline teaching;

[0092] Build a student information database;

[0093] The student information database includes the following information:

[0094] Number of students, names of students, grades of students, periodic examination scores of students and names of teachers;

[0095] The number of students records the total number of students in each class or course, which helps to understand the scale of teaching and resource allocation. The student name is used to identify and distinguish different students and ensure the accuracy of information recording. The student grade identifies the educational stage of the student and helps to analyze the learning characteristics and needs of students of different grades. The student's stage-by-stage test scores record the student's test scores at the end of each learning stage, which reflects the student's learning outcomes in a specific time period.

[0096] The name of the instructor, which records the identity of the instructor, helps to evaluate the relationship between the instructor's teaching effectiveness and student learning outcomes.

[0097] The student's stage test scores are to record the student's test scores at the end of each learning stage;

[0098] The periodic examination results are divided into grades, which are recorded as grade assessment;

[0099] The grades are graded as follows:

[0100] The corresponding score range for the first grade level is [95,100] points;

[0101] The corresponding score range for the second grade is [80,95] points;

[0102] The corresponding score range for the third grade is [60,80] points;

[0103] The score range for the fourth grade is [40,60] points;

[0104] According to the grade level assessment, obtain the standard weight of each level;

[0105] Build a database of teacher information;

[0106] The teaching teacher database includes the following information:

[0107] The name of the teacher, the teaching ability and effectiveness rating, and the score range available for teaching;

[0108] The database includes key information such as the number of students, names, grades, periodic examination scores and names of teachers, providing data support for the personalized management of educational training. By recording students' examination scores at the end of each learning stage, assessing the grades, and dividing the periodic examination scores into score ranges, it can provide targeted teaching support and resource allocation for students at different grades, thereby improving teaching effectiveness and student satisfaction. The standard weights of each level are obtained according to the grade level assessment. This weight distribution helps to optimize the allocation of teaching resources and construct a teacher information database, including the names of teachers, teaching ability effectiveness scores and teachable score ranges. This can quantitatively evaluate the teaching effectiveness of teachers and provide a basis for teachers' professional development and teaching improvement. By setting the teaching ability effectiveness scores and teachable score ranges, teacher resources can be allocated to ensure that students can obtain teaching support that matches their learning stage.

[0109] The teaching ability effectiveness score is a quantitative assessment of the teaching score of the teaching teacher in a specified grade range.

[0110] Optionally, the student's periodic examination results are the examination results of the student at the end of each learning stage, including:

[0111] Suppose S is the set of students' periodic examination scores, which contains the students' examination scores at the end of each learning stage, S = {s1, s2, ..., s n};

[0112] By setting the set S of students' periodic test scores, a comprehensive record and analysis of students' learning outcomes is achieved, which helps to deeply understand each student's learning progress and growth trajectory. By analyzing the positive and negative values ​​of the progress scores, the learning status of students can be identified;

[0113] where s i represents the score at the end of the i-th learning stage, and n is the total number of learning stages;

[0114] Set the progress score set P, P = {P1, P2, ..., P n-1};

[0115] Let P jis the progress score from the jth learning stage to the j+1th learning stage, and the calculation formula is:

[0116] P j =s j+1 -s j

[0117] This value reflects the difference in student achievement between two consecutive learning periods;

[0118] P j There are three cases for the value of , namely positive, zero, and negative;

[0119] Positive number: indicates that the student's performance has improved, i.e. s j+1 >s j ;

[0120] Zero: indicates that the student's grade has not changed, i.e. j+1 =s j ;

[0121] Negative number: indicates that the student's performance has declined, i.e. j+1 j ;

[0122] They represent whether students are making progress, not making progress, or regressing in their learning stages;

[0123] According to the grade level assessment, if P j If it corresponds to only one level score interval, the progress score of this learning stage will be implemented according to the first performance scoring strategy;

[0124] If P j Corresponding to multiple level score intervals, the improvement score of the learning stage is implemented with the second performance scoring strategy.

[0125] Furthermore, the step of obtaining the standard weights of each level according to the grade level evaluation includes:

[0126] According to the student information database, obtain the number of students, recorded as Q;

[0127] Get the number of students at the corresponding grade level at the end of the learning period, recorded as N i ,N i is the number of students in the i-th grade level;

[0128] Calculate the basic weight of each grade level, denoted as W i , W i is the basic weight of the i-th grade level, calculated by the following formula:

[0129]

[0130] ​By obtaining the standard weight of each level according to the grade level assessment, a quantitative assessment of the importance of the student's grade level is achieved. This helps to more accurately reflect the role of each grade level in educational practice, set the difficulty coefficient of the grade level, and adjust the weight of different grade levels;

[0131] Set the difficulty coefficient of the grade level, denoted as D i ,D i is the difficulty coefficient of the i-th grade level;

[0132] Get the upper limit score of the grade level, denoted as R i , R i is the upper limit score of the i-th grade level;

[0133] If it is the first achievement level, the upper limit score is 100 points;

[0134] If it is the second achievement level, the upper limit score is 95 points;

[0135] If it is the third achievement level, the upper limit score is 80 points;

[0136] If it is the fourth achievement level, the upper limit score is 60 points;

[0137] The difficulty coefficient calculation formula is:

[0138]

[0139] According to the difficulty coefficient and the basic weight, the standard weight is calculated and recorded as T i , is the standard weight of the i-th grade level, calculated by the following formula:

[0140]

[0141] Where m is the total number of grade levels.

[0142] Optionally, the above is determined based on the grade level assessment. If P j If there is only one level score interval, the progress score of the learning stage will be subject to the first performance scoring strategy, including:

[0143] According to the progress score P j , obtain the corresponding grade level standard weight;

[0144] The performance score of the corresponding grade level is calculated according to the following formula, denoted as K i :

[0145] K i =T i ×P j

[0146] Where Ti is the standard weight corresponding to the grade level;

[0147] By implementing the first performance scoring strategy, the progress scores of the learning stage corresponding to only one level score range are evaluated, which realizes the quantitative analysis of students' learning progress and improves the accuracy of students' progress evaluation. By obtaining the known standard weights of the corresponding grade level, it ensures that the evaluation of progress scores matches the students' actual learning outcomes.

[0148] Furthermore, if P j Corresponding to multiple level score intervals, the progress score of the learning stage is implemented with the second performance scoring strategy, including:

[0149] Get Progress Points P j For the corresponding learning stage, the test score at the end of the previous learning stage is recorded as the first score;

[0150] Get Progress Points P j The test score at the end of the corresponding learning phase is recorded as the second score;

[0151] If the level score interval of the first result does not match the level score interval of the second result, the improvement score P j The hierarchical score interval is divided into multiple sub-scores P j1 ,P j2 ,...,P jn ;

[0152] Each sub-score corresponds to a different level of achievement;

[0153] For each sub-score, execute the first performance scoring strategy and calculate the corresponding K i ;

[0154] The calculation formula is:

[0155] K i =T i ×P ji

[0156] The total performance score of each performance level is calculated based on the performance scores of different performance levels obtained according to the first performance score and the second performance score strategy.

[0157] By implementing the second performance scoring strategy, the progress scores across multiple grade level score ranges are evaluated, achieving a multi-dimensional quantitative analysis of students' learning progress. When students' grades span multiple levels, the sub-scores are subdivided to evaluate students' learning performance at each level. By obtaining the first and second grades and comparing their grade level score ranges, the specific progress of students at different learning stages can be identified.

[0158] Furthermore, according to the performance scores of different performance levels obtained by the first performance score and the second performance score strategy, the total performance score of each performance level is calculated, including:

[0159] Get the learning stage of the course taught by the teacher, recorded as the teaching stage;

[0160] According to the student information database, the test scores of students in the teaching stage are obtained;

[0161] Get the number of students in the corresponding grade level, recorded as A i , A i The number of students in each grade range corresponding to the teacher;

[0162] Calculate the total performance score for each grade level, denoted as U i , U i is the effectiveness score of the teacher corresponding to the i-th grade level;

[0163] Based on the total performance score of each grade level, the average performance score of each grade level is calculated.

[0164] Optionally, the total performance score of each grade level, and the average performance score of each grade level are calculated, including:

[0165] S1: Calculate the average performance score of each grade level, denoted as C i , the formula is:

[0166]

[0167] S2: Generate a score set based on the average performance score of the performance level, {C1, C2, ..., C n};

[0168] Sort the collection in descending order;

[0169] The sorted set is {C (1) , C (2) , ..., C (n)};

[0170] Get the average performance score C of the top three grades (1) , C (2) , C (3) ;

[0171] S3: C (1) , C (2) , C (3) The corresponding score range is marked as the teachable score range;

[0172] S4: It is recommended that teachers select students within the teaching score range for teaching;

[0173] Recommend students to select teachers to attend classes according to the score interval corresponding to the grade level of their own test scores at the end of the most recent learning stage. By calculating the total efficiency score of each grade level and further obtaining the average efficiency score, the evaluation of teaching effect is realized. In step S2, by generating a score set and sorting it, the grade level with the best teaching effect can be identified. This sorting mechanism helps educational managers and teachers to quickly grasp the advantages and areas that need improvement in teaching. Through step S3, the grade score interval corresponding to the average efficiency score of the top three grade levels is marked as the score interval that can be taught, which provides clear teaching focuses for teachers, helps to concentrate resources and attention to improve teaching quality. In step S4, the present invention recommends teachers to select students to teach in the score interval that can be taught. This strategy helps teachers to allocate teaching time and efforts more effectively, teach the student groups that are most likely to benefit, and allows students to select teachers to attend classes according to the score interval corresponding to the grade level of their own test scores at the end of the most recent learning stage.

[0174] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0175] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent management method for educational training based on big data, characterized by: include: Setting the teaching method of educational training, which includes online teaching and offline teaching; Build a student information database; The student information database includes the following information: Number of students, names of students, grades of students, periodic examination scores of students and names of teachers; The student's stage test scores are to record the student's test scores at the end of each learning stage; The periodic examination results are divided into grades, which are recorded as grade assessment; The grades are graded as follows: The corresponding score range for the first grade level is [95,100] points; The corresponding score range for the second grade is [80,95] points; The corresponding score range for the third grade is [60,80] points; The score range for the fourth grade is [40,60] points; According to the grade level assessment, obtain the standard weight of each level; Build a teacher information database; The teaching teacher database includes the following information: The name of the teacher, the teaching ability and effectiveness rating, and the score range available for teaching; The teaching ability effectiveness score is a quantitative assessment of the teaching score of the teaching teacher in a specified grade range.

2. The method for intelligent management of educational training based on big data according to claim 1 is characterized in that: The student's staged examination results are the examination results recorded at the end of each learning stage, including: Suppose S is the set of students' periodic examination scores, which contains the students' examination scores at the end of each learning stage, S = {s1, s2, ..., s n }; where s i represents the score at the end of the i-th learning stage, and n is the total number of learning stages; Set the progress score set P, P = {P1, P2, ..., P n-1 }; Let P j is the progress score from the jth learning stage to the j+1th learning stage, and the calculation formula is: P j =s j+1 -s j P j There are three cases for the value of , namely positive, zero, and negative; They represent whether students are making progress, not making progress, or regressing in their learning stages; According to the grade level assessment, if P j If it corresponds to only one level score interval, the progress score of this learning stage will be implemented according to the first performance scoring strategy; If P j Corresponding to multiple level score intervals, the improvement score of the learning stage is implemented with the second performance scoring strategy.

3. The method for intelligent management of educational training based on big data according to claim 1 is characterized in that: The standard weights of each level are obtained according to the grade level assessment, including: According to the student information database, obtain the number of students, recorded as Q; Get the number of students at the corresponding grade level at the end of the learning period, recorded as N i ,N i is the number of students in the i-th grade level; Calculate the basic weight of each grade level, denoted as W i , W i is the basic weight of the i-th grade level, calculated by the following formula: Set the difficulty coefficient of the grade level, denoted as D i ,D i is the difficulty coefficient of the i-th grade level; Get the upper limit score of the grade level, denoted as R i , R i is the upper limit score of the i-th grade level; If it is the first achievement level, the upper limit score is 100 points; If it is the second achievement level, the upper limit score is 95 points; If it is the third achievement level, the upper limit score is 80 points; If it is the fourth achievement level, the upper limit score is 60 points; The difficulty coefficient calculation formula is: According to the difficulty coefficient and the basic weight, the standard weight is calculated and recorded as T i , is the standard weight of the i-th grade level, calculated by the following formula: Where m is the total number of grade levels.

4. The method for intelligent management of educational training based on big data according to claim 2 is characterized in that: The above is determined based on the grade level assessment. If P j If there is only one level score interval, the progress score of the learning stage will be subject to the first performance scoring strategy, including: According to the progress score P j , obtain the corresponding grade level standard weight; The performance score of the corresponding grade level is calculated according to the following formula, denoted as K i : K i =T i ×P j Where T i It is the standard weight corresponding to the grade level.

5. The method for intelligent management of educational training based on big data according to claim 2 is characterized in that: If P j Corresponding to multiple level score intervals, the progress score of the learning stage is implemented with the second performance scoring strategy, including: Get progress points P j For the corresponding learning stage, the test score at the end of the previous learning stage is recorded as the first score; Get progress points P j The test score at the end of the corresponding learning phase is recorded as the second score; If the level score interval of the first result does not match the level score interval of the second result, the improvement score P j The hierarchical score interval is divided into multiple sub-scores P j1 ,P j2 ,...,P jn ; Each sub-score corresponds to a different level of achievement; For each sub-score, execute the first performance scoring strategy and calculate the corresponding K i ; The calculation formula is: K i =T i ×P ji The total performance score of each performance level is calculated based on the performance scores of different performance levels obtained according to the first performance score and the second performance score strategy.

6. The method for intelligent management of educational training based on big data according to claim 5 is characterized by: According to the performance scores of different grades obtained by the first performance score and the second performance score strategy, the total performance score of each grade level is calculated, including: Get the learning stage of the course taught by the teacher, recorded as the teaching stage; According to the student information database, the test scores of students in the teaching stage are obtained; Get the number of students in the corresponding grade level, recorded as A i , A i The number of students in each grade range corresponding to the teacher; Calculate the total performance score for each grade level, denoted as U i , U i is the effectiveness score of the teacher corresponding to the i-th grade level; Based on the total performance score of each grade level, the average performance score of each grade level is calculated.

7. The method for intelligent management of educational training based on big data according to claim 6 is characterized in that: The total performance score of each grade level, and the average performance score of each grade level are calculated, including: S1: Calculate the average performance score of each grade level, denoted as C i , the formula is: S2: Generate a score set based on the average performance score of the performance level, {C1, C2, ..., C n }; Sort the collection in descending order; The sorted set is {C (1) , C (2) , ..., C (n) }; Get the average performance score C of the top three grades (1) , C (2) , C (3) ; S3: C (1) , C (2) , C (3) The corresponding score range is marked as the teachable score range; S4: It is recommended that teachers select students within the teaching score range for teaching; Recommended students should select teachers to attend classes based on the score range corresponding to their test scores at the end of their most recent learning period.

Images