Smart home practical training teaching management system and method

Abstract

The invention belongs to the technical field of practical teaching management, and discloses a smart home practical teaching management system and method. Comprising the steps that a student data set is collected, and the student data set comprises student basic information ID and student learning ability information; preprocessing the student data set to obtain a preprocessed student data set; performing clustering processing on the preprocessed student data set to obtain a clustering processing result, and grouping the students based on the clustering processing result to obtain a grouped student data set; classified teaching management is carried out based on the grouped student data set; students are more accurately grouped by using the clustering algorithm, and classified teaching is performed according to the clustering result, so that teaching resources can be more effectively allocated, and the teaching effect is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of practical training teaching management, and more specifically, to a smart home practical training teaching management system and method. Background Art

[0002] The patent application publication number CN109919343A discloses a practical training teaching management method and management system, which relates to the field of practical training teaching management technology, and aims to solve the problem of low management efficiency of existing practical training teaching management methods. The key points of its technical solution are that the management method includes: entering the basic information of the internship base; obtaining the number information of the internship base that can be booked; sorting the number information of the internship base that can be booked in order from high to low according to the preset booking priority of each internship base and putting it into the idle library; obtaining the type information of the internship base selected by the trainee; taking out the number information of the internship base that is ranked first in the idle library and whose type information matches the type information selected by the trainee, and at the same time establishing a matching relationship between the number information of the taken internship base and the trainee and generating matching information; and assigning the matching information to the corresponding administrator for review. It greatly reduces the workload of the administrator and improves the management efficiency of the administrator.

[0003] With the increasing popularity of education, corresponding teaching methods should be adopted for students in different situations to ensure efficient teaching results; in the existing field of practical training teaching management technology, most teaching management methods are not accurate enough, resulting in unscientific student grouping and inappropriate teaching methods, causing some students to fail to keep up with the teaching progress, greatly reducing the teaching effect and also reducing management efficiency;

[0004] In view of this, the present invention proposes a smart home training teaching management system and method to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a smart home training teaching management method, comprising:

[0006] S1. Collect student data sets, which include student basic information ID and student learning ability information;

[0007] S2. preprocess the student data set to obtain a preprocessed student data set;

[0008] S3. Perform clustering processing on the preprocessed student data set to obtain a clustering processing result, and group the students based on the clustering processing result to obtain a grouped student data set;

[0009] S4. Implement classified teaching management based on the grouped student data set.

[0010] Furthermore, the student basic information ID includes the student name and student number; the student learning ability information includes historical average scores and historical GPAs; according to the student basic information ID, the historical average score and historical GPA of each student corresponding to the student basic information ID in the student system of the school are investigated to obtain the student learning ability information;

[0011] Combine the student basic information ID and the student learning ability information to obtain the student data set.

[0012] Furthermore, the method of preprocessing the student data set includes:

[0013] Preset a student data table, import the student data set into the student data table, use the student basic information ID, historical average score and historical GPA as the columns of the student data table, and use the number of students as the rows of the student data table; clean the student data table, and the data cleaning methods include processing missing values ​​and standardization; integrate the preprocessed data to obtain the preprocessed student data set.

[0014] Furthermore, the method of processing missing values ​​includes:

[0015] Use spreadsheet software to traverse the historical average score column and historical GPA column of the student data table column by column, scan the missing values ​​in the column and replace the missing values ​​with NULL; traverse the student data table row by row, mark the rows with NULL in the table, and take corresponding processing methods according to the number of NULL;

[0016] If the value of the historical average score column or the historical GPA column in the row is NULL, the conversion formula of the historical average score and historical GPA is used for calculation;

[0017] The calculation formula is score = GPA × 0.05; use the calculation results to fill in the missing values ​​of the corresponding columns;

[0018] If the values ​​of the historical average score column and the historical grade point average GPA column in this row are both NULL, the average values ​​of the non-missing values ​​in the corresponding columns are calculated to fill the missing values.

[0019] Furthermore, the formula for the standardization process is:

[0020] Among them, zi represents the historical average score after standardization; xi represents the historical average score in the original data; μi represents the mean of the historical average score; σ irepresents the standard deviation of the historical average score; n represents the number of students;

[0021] Among them, zj represents the historical GPA after standardization; xj represents the historical GPA in the original data; μ j Represents the mean of historical GPA; σ j Indicates the standard deviation of historical GPA.

[0022] Furthermore, the method of clustering the preprocessed student data set includes:

[0023] Based on the preprocessed student data set, calculate the distance between the data points represented by the historical average scores and historical GPAs of different students Where d(i, j) represents the distance between data points; zi represents the historical average score after standardization, zi* represents the historical average score of other students after standardization; z j represents the GPA after standardized processing, z j * It represents the standardized GPA of other students;

[0024] The silhouette coefficient is calculated based on the distance d(i, j), cohesion a(i, j) and separation b(i, j) between data points. Among them, a(i, j) represents cohesion, b(i, j) represents separation, and max represents the maximum value;

[0025] Cohesion Where d(i, j) represents the distance between data points; n represents the number of students, that is, the number of data points in the cluster;

[0026] Separation Where d(i, j) represents the distance between data points; C j Indicates the cluster where the current data point is located, C i represents adjacent clusters;

[0027] Calculate the average silhouette coefficient based on the silhouette coefficient S1 Among them, S1 represents the silhouette coefficient;

[0028] The initial number of clusters is preset. During the clustering process, the numerical value of the number of clusters is adjusted several times. Each time the number of clusters is adjusted, the average silhouette coefficient SC is calculated and recorded. The number of clusters corresponding to the largest average silhouette coefficient SC is taken as the optimal number of clusters K.

[0029] Based on the determined optimal clustering number K, the preprocessed student data set is processed to obtain cluster labels; the students are classified based on the cluster labels to obtain the grouped student data set;

[0030] The numerical range of the optimal clustering number K is constrained to be in, Express Take the integer.

[0031] Furthermore, the method of adjusting the number of clusters includes:

[0032] Execute clustering algorithm on the preprocessed student data set and select Different data points are used as the preset cluster centers P n And calculate the data point x and the preset cluster center P n The distance d(x, P n ), assign the data points to the nearest preset cluster center P n The corresponding cluster E i middle;

[0033] Calculate the preset cluster center P n The distance d(P m , P y ), where m = 1, ..., n, y = 1, ..., n; the two closest clusters are combined into a new cluster E j ; Each time clusters are merged, the current number of clusters is counted as the current number of clusters.

[0034] Furthermore, the method of processing the preprocessed student data set includes:

[0035] Randomly select K different data points from the preprocessed student data set as the initial cluster centers, namely C 1 , C 2 , ..., C K ; Calculate the data point x and cluster center C in the preprocessed student data set n The distance between them is d(x,C n );

[0036] Based on the calculated distance, each data point in the preprocessed student dataset is assigned to the cluster corresponding to the nearest cluster center;

[0037] Calculate the mass points of each cluster and use the mass points as the new cluster centers; repeat the allocation and acquisition of new cluster centers, preset the cluster center change threshold W, until the change rate of the cluster center is less than the cluster center change threshold W, then clustering is completed; obtain K clusters; label the students corresponding to the data points in the same cluster with the same cluster label; a total of K cluster labels.

[0038] Furthermore, classified teaching management is implemented for the grouped students based on the grouped student data set.

[0039] A smart home training teaching management system, which is used to implement the smart home training teaching management method, is characterized by comprising:

[0040] The data collection module is used to collect student data sets, which include student basic information ID and student learning ability information;

[0041] A preprocessing module is used to preprocess the student data set to obtain a preprocessed student data set;

[0042] The grouping module performs clustering processing on the preprocessed student data set to obtain a clustering processing result, and groups the students based on the clustering processing result to obtain a grouped student data set;

[0043] The classification management module implements classification teaching management based on the grouped student data set; each module is connected by wired and / or wireless means.

[0044] The technical effects and advantages of the smart home training teaching management system and method of the present invention are as follows:

[0045] By collecting student data sets, preprocessing the student data sets, cleaning the data, and clustering the preprocessed student data sets through clustering algorithms, students are grouped, classified teaching management is implemented, and corresponding teaching methods are implemented for students in different groups; compared with existing experience, using clustering algorithms to group students is more accurate, and classified teaching based on clustering results can more effectively allocate teaching resources. Teachers teach students with different learning abilities in accordance with their aptitude, improve teaching strategies, and enhance teaching effectiveness; based on clustering result analysis, potential problems in student groups can be discovered, so that timely intervention can be made; implementing corresponding teaching methods for students with different learning abilities promotes teaching fairness and ensures that every student can obtain teaching resources and attention that suits them; BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a smart home training teaching management method of the present invention;

[0047] Figure 2 A schematic diagram of a smart home training teaching management system of the present invention; DETAILED DESCRIPTION

[0048] 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.

[0049] Example 1

[0050] See also Figure 1 As shown, the smart home training teaching management method described in this embodiment includes:

[0051] S1. Collect student data sets, which include student basic information ID and student learning ability information;

[0052] S2. preprocess the student data set to obtain a preprocessed student data set;

[0053] S3. Perform clustering processing on the preprocessed student data set to obtain a clustering processing result, and group the students based on the clustering processing result to obtain a grouped student data set;

[0054] S4. Implement classified teaching management based on the grouped student data set.

[0055] The student basic information ID includes the student name and student number; the student learning ability information includes historical average scores and historical GPAs; according to the student basic information ID, the historical average score and historical GPA of each student corresponding to the student basic information ID in the school's student system are investigated to obtain the student learning ability information;

[0056] Combine the student basic information ID and the student learning ability information to obtain the student data set.

[0057] The methods for preprocessing the student dataset include:

[0058] Preset a student data table, import the student data set into the student data table, use the student basic information ID, historical average score and historical GPA as the columns of the student data table, and use the number of students as the rows of the student data table; clean the student data table, and the data cleaning methods include processing missing values ​​and standardization; integrate the preprocessed data to obtain the preprocessed student data set.

[0059] Ways to handle missing values ​​include:

[0060] Use spreadsheet software (such as Excel, use Excel plug-ins to implement traversal functions) to traverse the historical average score column and historical GPA column of the student data table column by column, scan the missing values ​​in the column and replace the missing values ​​with NULL; traverse the student data table row by row, mark the rows with NULL in the table, and take corresponding processing methods according to the number of NULL;

[0061] If the value of the historical average score column or the historical GPA column in the row is NULL, the conversion formula of the historical average score and historical GPA is used for calculation;

[0062] The calculation formula is score = GPA × 0.05; use the calculation results to fill in the missing values ​​of the corresponding columns;

[0063] If the values ​​of the historical average score column and the historical grade point average GPA column in this row are both NULL, the average values ​​of the non-missing values ​​in the corresponding columns are calculated to fill the missing values.

[0064] The formula for standardization is:

[0065] Among them, zi represents the historical average score after standardization; xi represents the historical average score in the original data; μ i Represents the mean of the historical average score; σ i represents the standard deviation of the historical average score; n represents the number of students;

[0066] Among them, zj represents the historical GPA after standardization; xj represents the historical GPA in the original data; μ j Represents the mean of historical GPA; σ j Indicates the standard deviation of historical GPA.

[0067] The methods for clustering the preprocessed student data set include:

[0068] Based on the preprocessed student data set, calculate the distance between the data points represented by the historical average scores and historical GPAs of different students Where d(i, j) represents the distance between data points; zi represents the historical average score after standardization, zi* represents the historical average score of other students after standardization; zj represents the historical GPA after standardization, zj * Represents the standardized GPA of other students.

[0069] The silhouette coefficient is calculated based on the distance d(i, j), cohesion a(i, j) and separation b(i, j) between data points. Among them, a(i, j) represents cohesion, b(i, j) represents separation, and max represents the maximum value;

[0070] Cohesion Where d(i, j) represents the distance between data points; n represents the number of students, that is, the number of data points in the cluster;

[0071] Separation Where d(i, j) represents the distance between data points; C j Indicates the cluster where the current data point is located, C i represents adjacent clusters;

[0072] Calculate the average silhouette coefficient based on the silhouette coefficient S1 Where S1 represents the silhouette coefficient.

[0073] The initial number of clusters is preset (for example, if the number of clusters is set to 4, the students are divided into four types, including students L1 with excellent learning ability, students L2 with good learning ability, students L3 with average learning ability, and students L4 with poor learning ability). During the clustering process, the numerical value of the number of clusters is adjusted several times. Each time the number of clusters is adjusted, the average silhouette coefficient SC is calculated and recorded, and the number of clusters corresponding to the largest average silhouette coefficient SC is taken as the optimal number of clusters K;

[0074] Set the K value range to in, Express Take the integer.

[0075] The method of adjusting the number of clusters includes:

[0076] Execute clustering algorithm on the preprocessed student data set and select Different data points (representing student information) are used as the preset cluster center P n And calculate the data point x and the preset cluster center P n The distance d(x, P n ), assign the data points to the nearest preset cluster center P n The corresponding cluster E i middle;

[0077] Calculate the preset cluster center P n The distance d(P m , P y ), where m = 1, ..., n, y = 1, ..., n; the two closest clusters are combined into a new cluster E j; Each time clusters are merged, the current number of clusters is counted as the current number of clusters.

[0078] The method of processing the preprocessed student data set includes:

[0079] Randomly select K different data points from the preprocessed student data set as the initial cluster centers, namely C 1 , C 2 , ..., C K ; Calculate the data point x and cluster center C in the preprocessed student data set n The distance between them is d(x, C n );

[0080] Based on the calculated distance, each data point in the preprocessed student dataset is assigned to the cluster corresponding to the nearest cluster center;

[0081] Calculate the mass points of each cluster and use the mass points as the new cluster centers; repeatedly perform the allocation and acquisition of new cluster centers, preset the cluster center change threshold W, until the change rate of the cluster center (for example, there are 100 points in the cluster, and due to repeated data point allocation operations, 20 data points are allocated to other clusters, and the change rate is 20%) is less than the cluster center change threshold W, then the clustering is completed; obtain K clusters; label the students corresponding to the data points in the same cluster with the same cluster label; a total of K cluster labels;

[0082] It should be noted that the cluster labels are classified based on students' historical average scores and historical GPAs. Students with similar historical average scores and historical GPAs are assigned to the same cluster. This method assigns students with similar academic performance to the same group, which can effectively promote communication and discussion among students, making it less likely for students to fall behind in the learning progress, thereby improving teaching efficiency.

[0083] Based on the grouped student data set, classified teaching management is implemented for the grouped students.

[0084] It should be noted that according to the grouping of the student data set after grouping, the system arranges corresponding teaching methods for students in different groups. For example, in the smart home logic circuit control course, the teaching method is:

[0085] For students with poor learning ability, the teaching method is: on the basis of teaching basic smart home logic circuit control, the teacher will make a return visit after class to answer questions and solve doubts for students with poor learning ability;

[0086] For students with average learning ability, the teaching method is: the teacher teaches them the basic smart home logic circuit control and assigns corresponding homework after the course;

[0087] For students with good learning ability, the teaching method is: the teacher mainly teaches the key contents of smart home logic circuit control and assigns homework. The rest of the content requires students to study on their own after class using the materials released by the teacher. If there are any questions, they can consult the teacher.

[0088] For students with excellent learning ability, the teaching method is as follows: teachers mainly teach the key contents of smart home logic circuit control and assign homework, arrange students to participate in skill competition selection after class, and carry out skill reinforcement training at the same time to guide students to expand the control functions of smart home logic circuits.

[0089] This embodiment collects student data sets, pre-processes the student data sets, cleans the data, and then clusters the pre-processed student data sets through a clustering algorithm, groups students, implements classified teaching management, and implements corresponding teaching methods for students in different groups; compared with existing experience, it is more accurate to group students using a clustering algorithm, and classified teaching based on clustering results can more effectively allocate teaching resources. Teachers teach students with different learning abilities in accordance with their aptitude, improve teaching strategies, and enhance teaching effectiveness; based on the analysis of clustering results, potential problems in student groups can be discovered, so that timely intervention can be made; implementing corresponding teaching methods for students with different learning abilities promotes teaching fairness and ensures that each student can obtain teaching resources and attention that suits him or her.

[0090] Example 2

[0091] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides a smart home training teaching management system, including:

[0092] The data collection module is used to collect student data sets, which include student basic information ID and student learning ability information;

[0093] A preprocessing module is used to preprocess the student data set to obtain a preprocessed student data set;

[0094] A grouping module is used to perform clustering processing on the pre-processed student data set to obtain a clustering processing result, and group the students based on the clustering processing result to obtain a grouped student data set;

[0095] The classification management module implements classification teaching management based on the grouped student data set; each module is connected by wired and / or wireless means.

[0096] Example 3

[0097] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the smart home practical training teaching management method provided above is implemented.

[0098] Since the electronic device introduced in this embodiment is an electronic device used to implement a smart home practical teaching management method in the embodiment of this application, based on the smart home practical teaching management method introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the smart home practical teaching management method in the embodiment of this application, it belongs to the scope of protection of this application.

[0099] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0100] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A smart home training teaching management method, characterized in that: include: S1. Collect student data sets, which include student basic information ID and student learning ability information; S2. preprocess the student data set to obtain a preprocessed student data set; S3. Perform clustering processing on the preprocessed student data set to obtain a clustering processing result, and group the students based on the clustering processing result to obtain a grouped student data set; S4. Implement classified teaching management based on the grouped student data set.

2. A smart home training teaching management method according to claim 1, characterized in that: The student basic information ID includes the student name and student number; the student learning ability information includes historical average scores and historical GPAs; according to the student basic information ID, the historical average score and historical GPA of each student corresponding to the student basic information ID in the school's student system are investigated to obtain the student learning ability information; Combine the student basic information ID and the student learning ability information to obtain the student data set.

3. A smart home training teaching management method according to claim 2, characterized in that: The method of preprocessing the student data set includes: Preset a student data table, import the student data set into the student data table, use the student basic information ID, historical average score and historical GPA as the columns of the student data table, and use the number of students as the rows of the student data table; clean the student data table, and the data cleaning methods include processing missing values ​​and standardization; integrate the preprocessed data to obtain the preprocessed student data set.

4. A smart home training teaching management method according to claim 3, characterized in that: The methods for handling missing values ​​include: Use spreadsheet software to traverse the historical average score column and historical GPA column of the student data table column by column, scan the missing values ​​in the column and replace the missing values ​​with NULL; traverse the student data table row by row, mark the rows with NULL in the table, and take corresponding processing methods according to the number of NULL; If the value of the historical average score column or the historical GPA column in the row is NULL, the conversion formula of the historical average score and historical GPA is used for calculation; The calculation formula is score = GPA × 0.05; use the calculation results to fill in the missing values ​​of the corresponding columns; If the values ​​of the historical average score column and the historical grade point average GPA column in this row are both NULL, the average values ​​of the non-missing values ​​in the corresponding columns are calculated to fill the missing values.

5. A smart home training teaching management method according to claim 4, characterized in that: The formula for the standardization process is: Among them, zi represents the historical average score sCore after standardization; xi represents the historical average score score in the original data; μi represents the mean of the historical average score score; σ i represents the standard deviation of the historical average score; n represents the number of students; Among them, zj represents the historical GPA after standardization; xj represents the historical GPA in the original data; μ j Represents the mean of historical GPA; σ j Indicates the standard deviation of historical GPA.

6. A smart home training teaching management method according to claim 5, characterized in that: The method of clustering the preprocessed student data set includes: Based on the preprocessed student data set, calculate the distance between the data points represented by the historical average scores and historical GPAs of different students Among them, d(i, j) represents the distance between data points; zi represents the historical average score after standardization, zi * represents the standardized historical average score of other students; zj represents the standardized historical GPA, zj * It represents the standardized GPA of other students; The silhouette coefficient is calculated based on the distance d(i, j), cohesion a(i, j) and separation b(i, j) between data points. Among them, a(i, j) represents cohesion, b(i, j) represents separation, and max represents the maximum value; Cohesion Where d(i, j) represents the distance between data points; n represents the number of students, that is, the number of data points in the cluster; Separation Where d(i, j) represents the distance between data points; C j Indicates the cluster where the current data point is located, C i represents adjacent clusters; Calculate the average silhouette coefficient based on the silhouette coefficient S1 Where S1 represents the silhouette coefficient; The initial number of clusters is preset. During the clustering process, the numerical value of the number of clusters is adjusted several times. Each time the number of clusters is adjusted, the average silhouette coefficient SC is calculated and recorded. The number of clusters corresponding to the largest average silhouette coefficient SC is taken as the optimal number of clusters K. Based on the determined optimal clustering number K, the preprocessed student data set is processed to obtain cluster labels; the students are classified based on the cluster labels to obtain the grouped student data set; The numerical range of the optimal clustering number K is constrained to be in, Express Take the integer.

7. A smart home training teaching management method according to claim 6, characterized in that: The method of adjusting the number of clusters includes: Execute clustering algorithm on the preprocessed student data set and select Different data points are used as the preset cluster centers P n And calculate the data point x and the preset cluster center P n The distance d(x, P n ), assign the data points to the nearest preset cluster center P n The corresponding cluster E i middle; Calculate the preset cluster center P n The distance d(P m , P y ), where m = 1, ..., n, y = 1, ..., n; the two closest clusters are combined into a new cluster E j ; Each time clusters are merged, the current number of clusters is counted as the current number of clusters.

8. A smart home training teaching management method according to claim 7, characterized in that: The method of processing the preprocessed student data set includes: Randomly select K different data points from the preprocessed student data set as the initial cluster centers, namely C1, C2, ..., C K ; Calculate the data point x and cluster center C in the preprocessed student data set n The distance between them is d(x, C n ); Based on the calculated distance, each data point in the preprocessed student dataset is assigned to the cluster corresponding to the nearest cluster center; Calculate the mass points of each cluster and use the mass points as the new cluster centers; repeat the allocation and acquisition of new cluster centers, preset the cluster center change threshold W, until the change rate of the cluster center is less than the cluster center change threshold W, then clustering is completed; obtain K clusters; label the students corresponding to the data points in the same cluster with the same cluster label; a total of K cluster labels.

9. A smart home training teaching management method according to claim 8, characterized in that: Based on the grouped student data set, classified teaching management is implemented for the grouped students.

10. A smart home training teaching management system, which is used to implement a smart home training teaching management method according to any one of claims 1 to 9, characterized in that: include: The data collection module is used to collect student data sets, which include student basic information ID and student learning ability information; A preprocessing module is used to preprocess the student data set to obtain a preprocessed student data set; The grouping module performs clustering processing on the preprocessed student data set to obtain a clustering processing result, and groups the students based on the clustering processing result to obtain a grouped student data set; The classification management module implements classification teaching management based on the grouped student data set; each module is connected by wired and / or wireless means.

Images