Physical education activity management system and method based on behavior analysis
Through the management method of physical education teaching activities based on behavior analysis, the problems of inefficient and subjective traditional physical education teaching management are solved, more accurate evaluation and personalized teaching strategies are achieved, and the quality and efficiency of teaching management are improved.
Patent Information
- Application Number
- CN202411067178.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional physical education teaching management relies on manual observation and recording, is inefficient and vulnerable to subjective factors, resulting in inaccurate and comprehensive evaluation results.
Adopt the management method of physical education teaching activities based on behavior analysis, and by collecting and quantifying behavioral parameters of students and teachers, generating behavioral parameter curves, extracting key features, matching them with preset databases, outputting evaluation instructions, and automatically identifying behavior patterns and trends to improve Accuracy and efficiency of teaching management.
It has achieved a more accurate and comprehensive assessment of the behavioral status of students and teachers, provided personalized learning strategies, improved the quality and efficiency of teaching management, and timely discovered teaching problems and made adjustments.
Smart Images

Figure CN119091498A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of teaching management, and in particular relates to a sports teaching activity management system and method based on behavior analysis. Background Art
[0002] In physical education teaching activities, management is a complex and critical task, which covers teaching arrangements, teacher-student interaction, teaching evaluation and other links. However, traditional physical education teaching management often relies on manual observation and recording, which is not only inefficient, but also easily affected by subjective factors, resulting in inaccurate and incomplete evaluation results. The limitations of the existing system are as follows: strong subjectivity, incomplete data collection, limited analysis methods, and insufficient application of information technology. It is particularly important to develop a physical education teaching activity management system and method based on behavior analysis. Summary of the invention
[0003] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the first purpose of the present invention is to provide a physical education teaching activity management method based on behavior analysis; the second purpose of the present invention is to provide a physical education teaching activity management system based on behavior analysis.
[0004] The first object of the present invention adopts the following technical solution:
[0005] The physical education teaching activity management method based on behavioral analysis, the method flow is as follows:
[0006] Step 1: Collect and quantify student behavior parameters during teaching activities, including student action execution accuracy, student concentration, student participation, number of student distraction, and other student behavior parameters;
[0007] Step 2: Generate a student behavior parameter curve, extract key student behavior parameter features of the student behavior parameter curve; analyze the key student behavior parameter features, determine the student behavior analysis results, and match them with the preset first database to obtain the student behavior status evaluation results;
[0008] Wherein, the first database stores the corresponding relationship between the student behavior analysis results and the student behavior status assessment results;
[0009] Step 3: Outputting student behavior analysis evaluation instructions, which are divided into a first regular teaching activity evaluation instruction and a second special teaching activity evaluation instruction;
[0010] Step 4: Collect and quantify teaching preparation behavior parameters, including teaching explanation clarity, teaching action demonstration accuracy, teaching interaction frequency, teaching resource preparation adequacy, teaching plan execution, and other teaching preparation behavior parameters;
[0011] Step 5: Generate the teaching preparation behavior parameter curve, extract the key teaching preparation behavior characteristics of the teaching preparation behavior parameter curve; analyze the key teaching preparation behavior parameter characteristics, determine the teaching preparation behavior parameter analysis result; and match it with the preset second database to obtain the teaching preparation behavior parameter status evaluation result;
[0012] Among them, the second database stores the corresponding relationship between the teaching preparation behavior analysis result and the teaching preparation behavior status evaluation result;
[0013] Step 6: Output the teaching preparation behavior analysis and evaluation instructions, which are divided into the third regular teaching activity evaluation instruction and the fourth special teaching activity evaluation instruction.
[0014] Preferably, the first database stores the corresponding relationship between the student behavior analysis result and the student behavior status evaluation result, and also includes the student's characteristic information and its index; the second database stores the corresponding relationship between the teaching preparation behavior analysis result and the teaching preparation behavior status evaluation result, and also includes the teacher's characteristic information and its index.
[0015] Preferably, the process of generating the student behavior parameter curve and extracting the key student behavior parameter characteristics of the student behavior parameter curve is as follows:
[0016] Convert the discrete student behavior parameter curve into a continuous curve, calculate the deviation between the student behavior parameter curve and the student average curve to obtain a deviation curve, and then perform an interpolation smoothing operation on the deviation curve to convert it into a continuous deviation curve; the student average curve refers to the average performance level of students of the same age group;
[0017] Any point between two adjacent points on the deviation curve lies on the line connecting these two points. Assuming these two points are (a1, b1) and (a2, b2) respectively, and the interpolation point is (a, b), then it satisfies
[0018] Given any a1 < a < a2, by analyzing the above formula, the linear interpolation target value b corresponding to a is obtained:
[0019]
[0020] Perform equally spaced sampling on the continuous deviation curve of the student behavior parameter, sample every time T1, and obtain the n-dimensional feature vector point x = (x1, x2, x3,..., x n ); The n-dimensional feature vector is used to identify the behavior patterns of different students.
[0021] Preferably, the process of analyzing the key student behavior parameter characteristics and determining the student behavior analysis result is as follows:
[0022] Take any feature vector xn As the center of the circle, set the radius to r to form a circular area, and mark the set of all points in this circular area as neighborhood B r (x n );B r (x n )={x p ∈D│dist(x n ,x p )≤r}; where dist(x n ,x p ) represents x n and x p The distance between them; mark the minimum number of samples in the neighborhood as MinPts; randomly select a point x from x n , judge |B r (x n )|is greater than or equal to MinPts, when|B r (x n )|≥MinPts, then determine x n As a core object, add it to the core set Z;
[0023] A core object xn is randomly selected from the core set Z, and all points that are density-reachable are added to the new set C1 to form the first critical area of student behavior; where density-reachable is defined as follows: p In x n In the neighborhood of n is a core object, then x p By x n Density direct, if there exists a1,a2,...,a n , where a1 = x n , a n =x p , and a i+1 By a i The density is directly proportional to x p By x n Density can reach;
[0024] Continue to visit the next point in x and repeat the above steps until all points in x are processed to obtain u student behavior key areas. The points not included in the student behavior key areas are marked as noise and deleted; the student behavior key areas include u different student behavior areas.
[0025] Preferably, the process of matching with the preset first database to obtain the student behavior status evaluation result is as follows:
[0026] Retrieve relevant indexes in the first database according to the key student behavior parameter characteristics of the key areas of student behavior belonging to the student to be matched, select at least one pre-matched student, and form a set of pre-matched students; use each pre-matched student in the set of pre-matched students as a comparison student respectively;
[0027] Calculate the similarity between the behavior parameter characteristics of the student to be matched and those of the comparison student, including the similarity of action execution accuracy, the similarity of attention concentration, the similarity of student participation, the similarity of the number of attention dispersions, and the similarity of other behavior characteristics; calculate the overall behavior state similarity between the student to be matched and the comparison student, and the calculation formula is as follows: Where n is the number of types of behavior characteristic information; i is a positive integer from 1 to n; S i Is the similarity between the behavior parameter characteristics of the i-th student to be matched and those of the comparison student; W i Is the weight coefficient corresponding to S i ; S student Is the overall behavior similarity between the student to be matched and the comparison student;
[0028] If the overall behavior state similarity of student A is greater than the set threshold, it indicates that his performance is good, output the first regular teaching activity evaluation instruction, and maintain the current teaching activity; if the overall behavior state similarity of student A is less than or equal to the set threshold, it indicates that special attention is needed, output the second special teaching activity evaluation instruction, including increasing individual tutoring, changing teaching methods, and improving participation.
[0029] Preferably, generate a teaching preparation behavior parameter curve, and the process of extracting the key teaching preparation behavior characteristics of the teaching preparation behavior parameter curve is as follows:
[0030] Convert the discrete teaching preparation behavior parameter curve into a continuous curve, calculate the difference between the teaching preparation behavior parameter curve and the group average value curve to obtain a deviation curve; the group average value curve refers to the average level of the teacher group; perform interpolation processing on the deviation curve of the teaching preparation behavior parameters to convert it into a continuous deviation curve;
[0031] Any point between two adjacent points in the deviation curve is on the line connecting these two points. Assuming these two points are (c1, d1) and (c2, d2) respectively, and the interpolation point is (c, d), then it satisfies
[0032] Given any c1 < c < c2, by analyzing the above formula, obtain the linear interpolation target value d corresponding to c:
[0033]
[0034] The continuous deviation curve of the teaching preparation behavior parameter is sampled at equal intervals, and sampling is performed every time T2 to obtain the m-dimensional feature vector y=(y1, y2, y3, ..., y m ); the m-dimensional feature vector is used to identify different teaching preparation modes.
[0035] Preferably, the process of analyzing the key teaching preparation behavior parameter characteristics and determining the teaching preparation behavior parameter analysis results is as follows:
[0036] For any feature vector y m As the center of the circle, set the radius to r to form a circular area, and mark the set of all points in this circular area as neighborhood B r (y m );B r (y m )={y q ∈D│dist(y m ,y q )≤r}; where dist(y m ,y q ) represents x n and q The distance between them; the minimum number of samples in the neighborhood is marked as MinPts;
[0037] Randomly pick a point y from y m , judge |B r (y m )|is greater than or equal to MinPts, when|B r (y m )|≥MinPts, then determine y m As a core object, it is added to the core set Z1;
[0038] Randomly pick a core object y from the core set Z1 m , add all points that can be reached by its density to the new set C2 to form the first key area of teaching preparation behavior; where the definition of density reachability is as follows: if y q In y m In the neighborhood of m is a core object, then y q By m Density direct, if there exists a1,a2,...,a n , where a1 = y m , a n =y q , and a i+1 By a i The density is directly proportional to y q By m Density can reach;
[0039] Continue to visit the next point in y and repeat the above steps until all points in y are processed to obtain v key areas of teaching preparation behavior. Points not included in the key areas of teaching preparation behavior are marked as noise and deleted. The key areas of teaching preparation behavior include v different teaching preparation behavior areas.
[0040] Preferably, the process of matching with the preset second database to obtain the teaching preparation behavior parameter status evaluation result is as follows:
[0041] Acquire at least one teaching preparation behavior parameter feature of the teacher to be matched and the teaching preparation behavior parameter feature of the comparison teacher; retrieve relevant indexes in the second database according to the teaching preparation behavior parameter feature of the teacher to be matched belonging to the key area of the teaching preparation behavior, select at least one pre-matching teacher, and form a pre-matching teacher set; use each pre-matching teacher in the pre-matching teacher set as a comparison teacher;
[0042] Calculate the similarity between the teaching preparation behavior parameter characteristics of the matching teacher and the comparison teacher, including the similarity of teaching explanation clarity, teaching action demonstration accuracy, teaching interaction frequency, teaching resource preparation adequacy, teaching plan execution, and other teaching preparation behavior characteristics; calculate the overall teaching preparation behavior similarity between the matching teacher and the comparison teacher, and the calculation formula is as follows: Where m is the number of behavior parameter feature types prepared for teaching; j is a positive integer from 1 to m; S j is the similarity between the teaching preparation behavior parameter characteristics of the jth matching teacher and the teaching preparation behavior parameter characteristics of the comparison teacher; S teacher The similarity of the overall teaching preparation behavior parameter characteristics between the matched teacher and the comparison teacher;
[0043] If the similarity of teacher B's overall teaching preparation behavior is greater than the set threshold, it indicates that he is well prepared, and the third regular teaching activity evaluation instruction is output to maintain the current teaching preparation activity; if the similarity of teacher B's overall teaching preparation behavior is less than or equal to the set threshold, it indicates that special attention is needed, and the fourth special teaching activity evaluation instruction is output, including increasing preparation time and improving teaching resources.
[0044] The second object of the present invention adopts the following technical solution:
[0045] A sports teaching activity management system based on behavior analysis comprises a data acquisition module, a data processing module, a feature extraction module, an analysis and matching module, an instruction output module, a first database and a second database; the data acquisition module is used to collect student behavior parameters and teaching preparation behavior parameters; the data processing module is used to quantify and integrate parameters, generate student behavior parameter curves and teaching preparation behavior parameter curves; the feature extraction module is used to extract key student behavior parameter features and key teaching preparation behavior features; the analysis and matching module is used to analyze key student behavior parameter features, determine student behavior analysis results, and match them with a preset first database to obtain student behavior status evaluation results, analyze key teaching preparation behavior parameter features, determine teaching preparation behavior parameter analysis results, and match them with a preset second database to obtain teaching preparation behavior parameter status evaluation results; the instruction output module is used to output student behavior analysis evaluation instructions and teaching preparation behavior analysis evaluation instructions; the first database is used to store the corresponding relationship between student behavior analysis results and student behavior status evaluation results; the second database is used to store the corresponding relationship between teaching preparation behavior analysis results and teaching preparation behavior status evaluation results.
[0046] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0047] 1. Based on the analysis of students' behavior parameter curves and feature vectors, the present invention can identify students' specific behavior patterns, thereby providing them with more suitable learning strategies; by analyzing students' behavior parameter characteristics and matching them with data in a preset database, the present invention can quickly provide evaluation results of students' behavior status;
[0048] 2. The present invention converts discrete behavioral parameters and teaching preparation behavioral parameters into continuous curves, calculates the deviation from the average curve, and then performs interpolation and smoothing processing to form a continuous deviation curve. Finally, equal-interval sampling is performed to obtain a feature vector. This can more accurately capture the changing trends and abnormal points of student behaviors and teaching preparation behaviors, which is conducive to further data analysis.
[0049] 3. The present invention uses the DBSCAN algorithm to identify the behavioral patterns of different students and distinguish between core objects, non-core objects and noise points. This method can automatically discover student behavior clusters with high density, which helps to understand the behavioral distribution and differences within the student group.
[0050] 4. The present invention evaluates students' behavioral status and teaching preparation behavioral status by matching the behavioral analysis results in the preset first database and the second database, and outputs different teaching activity evaluation instructions accordingly, which helps to make teaching decisions quickly and improve the quality and efficiency of teaching management. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0052] Figure 1 A flow chart of a method for managing physical education activities based on behavior analysis of the present invention is shown.
[0053] Figure 2 The module diagram of the physical education teaching activity management system based on behavior analysis of the present invention is shown.
[0054] Figure 3 A flow chart of analyzing key teaching preparation behavior parameter characteristics of the present invention is shown. DETAILED DESCRIPTION
[0055] 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.
[0056] Example 1
[0057] See also Figure 1 As shown, the physical education teaching activity management method based on behavior analysis in this embodiment has the following process:
[0058] Step 1: Collect and quantify student behavior parameters during teaching activities, including student action execution accuracy, student concentration, student participation, number of student distraction, and other student behavior parameters;
[0059] Step 2: Generate a student behavior parameter curve, extract key student behavior parameter features of the student behavior parameter curve; analyze the key student behavior parameter features, determine the student behavior analysis results, and match them with the preset first database to obtain the student behavior status evaluation results;
[0060] Wherein, the first database stores the corresponding relationship between the student behavior analysis results and the student behavior status assessment results;
[0061] The first database includes characteristic information and indexes of several students.
[0062] Specifically:
[0063] S21. Convert the discrete student behavior parameter curve into a continuous curve, calculate the deviation between the student behavior parameter curve and the student average curve to obtain a deviation curve, and then perform an interpolation smoothing operation on the deviation curve to convert it into a continuous deviation curve. The student average curve refers to the average performance level of students of the same age group.
[0064] Any point between two adjacent points on the deviation curve lies on the line connecting these two points. Assume these two points are (a1, b1) and (a2, b2), and the interpolation point is (a, b), then it satisfies
[0065] Given any a1 < a < a2, by analyzing the above formula, obtain the linear
[0066] interpolation target value b:
[0067] Perform equally spaced sampling on the continuous deviation curve of the student behavior parameters, sample every time T1, and obtain an n-dimensional feature vector point x = (x1, x2, x3,..., x n ); The n-dimensional feature vector is used to identify the behavior patterns of different students.
[0068] Take any feature vector x n as the center and set the radius as r to form a circular region. Mark the set of all points within this circular region as the neighborhood B r (x n ),
[0069] B r (x n ) = {x p ∈D │ dist(x n , x p ) ≤ r};
[0070] Among them, dist(x n , x p ) represents the distance between x n and x p ;
[0071] Mark the minimum value of the number of samples within the neighborhood as MinPts;
[0072] Randomly select a point x n from x, and judge whether |B r (x n )| is greater than or equal to MinPts. When |B r (x n )| ≥ MinPts, then determine that x n is a core object and add it to the core set Z;
[0073] A core object xn is randomly selected from the core set Z, and all its density-reachable points are added to the new set C1 to form the first student behavior critical area; where density reachability is defined as follows: if x p In x n In the neighborhood of n is a core object, then x p By x n Density direct, if there exists a1,a2,...,a n , where a1 = x n , a n =x p , and a i+1 By a i The density is directly proportional to x p By x n Density can reach;
[0074] Continue to visit the next point in x and repeat the above steps until all points in x are processed and u student behavior key areas are obtained. The points not included in the student behavior key areas are marked as noise and deleted;
[0075] The Student Conduct Key Area includes 3 different areas of student conduct.
[0076] According to the key student behavior parameter characteristics of the students to be matched belonging to the key student behavior areas, relevant indexes are retrieved in the first database, and at least one pre-matching student is selected to form a pre-matching student set; each pre-matching student in the pre-matching student set is used as a comparison student.
[0077] Calculate the similarity between the behavioral parameter characteristics of the student to be matched and the behavioral parameter characteristics of the comparison student, including the similarity of action execution accuracy, attention concentration, student participation, distraction times, and other behavioral characteristics.
[0078] Calculate the similarity of the overall behavior status of the matching students and the comparison students. The calculation formula is as follows:
[0079]
[0080] Where n is the number of behavior feature information types; i is a positive integer from 1 to n; S i is the similarity between the behavior parameter characteristics of the i-th student to be matched and the behavior parameter characteristics of the comparison student; W i For S i The corresponding weight coefficient; S student is the overall behavioral similarity between the students to be matched and the comparison students.
[0081] Step 3: Output student behavior analysis and evaluation instructions, which are divided into the first regular teaching activity evaluation instructions and the second special teaching activity evaluation instructions;
[0082] If the overall behavior state similarity of student A is greater than the set threshold, it indicates that his performance is good, and the first regular teaching activity evaluation instructions are output to maintain the current teaching activity.
[0083] If the overall behavior state similarity of student A is less than or equal to the set threshold, it indicates that special attention is needed, and the second special teaching activity evaluation instructions are output, including increasing individual tutoring, changing teaching methods, and improving participation.
[0084] Step 4: Collect and quantify teaching preparation behavior parameters, including teaching explanation clarity, teaching action demonstration accuracy, teaching interaction frequency, teaching resource preparation sufficiency, teaching plan execution, and other teaching preparation behavior parameters;
[0085] Step 5: Generate a teaching preparation behavior parameter curve; extract the key teaching preparation behavior characteristics of the teaching preparation behavior parameter curve; analyze the key teaching preparation behavior parameter characteristics, determine the teaching preparation behavior parameter analysis result, and match it with the preset second database to obtain the teaching preparation behavior parameter status evaluation result.
[0086] Calculate the difference between the teaching preparation behavior parameter curve and the group average value curve to obtain a deviation curve; the group average value curve refers to the average level of the teacher group.
[0087] Interpolate the deviation curve of the teaching preparation behavior parameters to convert it into a continuous deviation curve;
[0088] Any point between two adjacent points on the deviation curve lies on the line connecting these two points. Assume these two points are (c1, d1) and (c2, d2), and the interpolation point is (c, d), then it satisfies
[0089] Given any c1 < c < c2, by analyzing the above formula, the linear
[0090] interpolation target value d is obtained:
[0091] Perform equally spaced sampling on the continuous deviation curve of the teaching preparation behavior parameters, sampling every time T2, to obtain an m-dimensional feature vector y = (y1, y2, y3,..., y m )
[0092] The m-dimensional feature vector is used to identify different teaching preparation modes.
[0093] Refer to Figure 3 As shown, for any feature vector ym As the center of the circle, set the radius to r to form a circular area, and mark the set of all points in this circular area as neighborhood B r (y m ),
[0094] B r (y m )={y q ∈D│dist(y m ,y q )≤r};
[0095] Among them, dist(y m ,y q ) represents x n and q The distance between
[0096] The minimum number of samples in the neighborhood is marked as MinPts;
[0097] Randomly pick a point y from y m , judge |B r (y m )|is greater than or equal to MinPts, when|B r (y m )|≥MinPts, then determine y m As a core object, it is added to the core set Z1;
[0098] Randomly pick a core object y from the core set Z1 m , add all points that can be reached by its density to the new set C2 to form the first key area of teaching preparation behavior; where the definition of density reachability is as follows: if y q In y m In the neighborhood of m is a core object, then y q By m Density direct, if there exists a1,a2,...,a n , where a1=y m , a n =y q , and a i+1 By a i The density reaches directly, then y q By m Density can reach;
[0099] Continue to visit the next point in y and repeat the above steps until all points in y are processed to obtain v key areas of teaching preparation behavior. The points not included in the key areas of teaching preparation behavior are marked as noise and deleted.
[0100] The key areas of teaching preparation behavior include v different teaching preparation behavior areas.
[0101] Among them, the second database stores the correspondence between the teaching preparation behavior analysis results and the teaching preparation behavior status evaluation results.
[0102] The second database includes characteristic information and indexes of several teachers.
[0103] Obtaining at least one teaching preparation behavior parameter feature of the teacher to be matched and the teaching preparation behavior parameter feature of the comparison teacher;
[0104] According to the teaching preparation behavior parameter characteristics of the teachers to be matched belonging to the key areas of teaching preparation behavior, relevant indexes are retrieved in the second database, and at least one pre-matching teacher is selected to form a pre-matching teacher set; each pre-matching teacher in the pre-matching teacher set is used as a comparison teacher.
[0105] Calculate the similarity between the teaching preparation behavior parameter characteristics of the teacher to be matched and the teaching preparation behavior parameter characteristics of the comparison teacher, including the similarity of teaching explanation clarity, the similarity of teaching action demonstration accuracy, the similarity of teaching interaction frequency, the similarity of teaching resource preparation adequacy, the similarity of teaching plan execution, and the similarity of other teaching preparation behavior characteristics.
[0106] Calculate the similarity of the overall teaching preparation behavior of the matching teacher and the comparison teacher. The calculation formula is as follows:
[0107]
[0108] Where m is the number of behavior parameter feature types prepared for teaching; j is a positive integer from 1 to m; S j is the similarity between the teaching preparation behavior parameter characteristics of the jth matching teacher and the teaching preparation behavior parameter characteristics of the comparison teacher; S teacher It is the similarity of the overall teaching preparation behavior parameter characteristics between the matched teacher and the comparison teacher.
[0109] Step 6: Output the teaching preparation behavior analysis evaluation instructions, which are divided into the third regular teaching activity evaluation instructions and the fourth special teaching activity evaluation instructions.
[0110] If the overall teaching preparation behavior similarity of teacher B is greater than the set threshold, it indicates that he is well prepared, and the third regular teaching activity evaluation instruction is output to maintain the current teaching preparation activity;
[0111] If the similarity of teacher B's overall teaching preparation behavior is less than or equal to the set threshold, it indicates that special attention is needed, and the fourth special teaching activity evaluation instruction is output, including increasing preparation time and improving teaching resources.
[0112] The beneficial effects of this embodiment are: improving the efficiency and quality of physical education teaching activities, and promoting the common development of teachers and students.
[0113] Example 2
[0114] See also Figure 2 As shown, the physical education teaching activity management system based on behavior analysis of this embodiment includes a data acquisition module, a data processing module, a feature extraction module, an analysis and matching module, an instruction output module, a first database, and a second database;
[0115] The data collection module is used to collect student behavior parameters and teaching preparation behavior parameters;
[0116] The data processing module is used to quantify the integration parameters and generate the student behavior parameter curve and the teaching preparation behavior parameter curve;
[0117] The feature extraction module is used to extract key student behavior parameter features of the student behavior parameter curve and key teaching preparation behavior features of the teaching preparation behavior parameter curve;
[0118] The analysis and matching module is used to analyze key student behavior parameter characteristics, determine student behavior analysis results, and match them with a preset first database to obtain student behavior status evaluation results, analyze key teaching preparation behavior parameter characteristics, determine teaching preparation behavior parameter analysis results, and match them with a preset second database to obtain teaching preparation behavior parameter status evaluation results;
[0119] The instruction output module is used to output student behavior analysis evaluation instructions and teaching preparation behavior analysis evaluation instructions; the first database is used to store the correspondence between student behavior analysis results and student behavior status evaluation results; the second database is used to store the correspondence between teaching preparation behavior analysis results and teaching preparation behavior status evaluation results.
[0120] The beneficial effects of this embodiment are: through the analysis results of student behavior and teaching preparation behavior, more personalized teaching strategies can be implemented to meet the teaching needs of different students, problems in the teaching process can be discovered in time and corresponding adjustments can be made, thereby improving teaching quality and efficiency.
[0121] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
[0122] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
[0123] Weight coefficient W i Used to measure the impact of different factors or variables on S i The degree of influence, weight coefficient W i The definition of is to assign a value to each factor to reflect its importance and priority when comparing and evaluating multiple factors; the weight coefficient W j Used to measure the impact of different factors or variables on S j The degree of influence, weight coefficient W j The definition of is to assign a value to each factor to reflect its importance and priority when comparing and evaluating multiple factors; the weight coefficient W i , W j It can be determined according to specific circumstances and needs. It is usually jointly formulated and confirmed by professionals or relevant stakeholders. It can be determined according to specific circumstances and needs. By reasonably setting the weight coefficient W i , W j It can help the system make decisions more accurately.
Claims
1. A sports teaching activity management method based on behavior analysis, characterized in that: The method process is as follows: Step 1: Collect and quantify the student behavior parameters during the teaching activity process, including the action execution accuracy of students, the attention concentration of students, the student participation rate, the number of times of student attention dispersion, and other student behavior parameters; Step 2: Generate a student behavior parameter curve, extract the key student behavior parameter features of the student behavior parameter curve; analyze the key student behavior parameter features, determine the student behavior analysis result, and match it with the preset first database to obtain the student behavior status evaluation result; Among them, the first database stores the correspondence between the student behavior analysis result and the student behavior status evaluation result; Step 3: Output student behavior analysis and evaluation instructions, which are divided into the first regular teaching activity evaluation instruction and the second special teaching activity evaluation instruction; Step 4: Collect and quantify the teaching preparation behavior parameters, including the clarity of teaching explanations, the accuracy of teaching action demonstrations, the frequency of teaching interactions, the sufficiency of teaching resource preparation, the implementation of the teaching plan, and other teaching preparation behavior parameters; Step 5: Generate a teaching preparation behavior parameter curve, extract the key teaching preparation behavior features of the teaching preparation behavior parameter curve; analyze the key teaching preparation behavior parameter features, determine the teaching preparation behavior parameter analysis result; and match it with the preset second database to obtain the teaching preparation behavior parameter status evaluation result; Among them, the second database stores the correspondence between the teaching preparation behavior analysis result and the teaching preparation behavior status evaluation result; Step 6: Output teaching preparation behavior analysis and evaluation instructions, which are divided into the third regular teaching activity evaluation instruction and the fourth special teaching activity evaluation instruction.
2. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The first database stores the correspondence between the student behavior analysis result and the student behavior status evaluation result, and also includes the characteristic information of students and their indexes; the second database stores the correspondence between the teaching preparation behavior analysis result and the teaching preparation behavior status evaluation result, and also includes the characteristic information of teachers and their indexes.
3. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of generating the student behavior parameter curve and extracting the key student behavior parameter features of the student behavior parameter curve is specifically as follows: Convert the discrete student behavior parameter curve into a continuous curve, calculate the deviation between the student behavior parameter curve and the student average curve to obtain a deviation curve, and then perform an interpolation smoothing operation on the deviation curve to convert it into a continuous deviation curve; the student average curve refers to the average performance level of students of the same age group; Any point between two adjacent points in the deviation curve is on the line connecting these two points. Assuming that the two points are (a1, b1) and (a2, b2), and the interpolation point is (a, b), then Given any a1 < a < a2, by analyzing the above formula, obtain the linear interpolation target value b corresponding to a: The continuous deviation curve of the student behavior parameter is sampled at equal intervals, and sampling is performed every time T1 to obtain the n-dimensional feature vector point x=(x1,x2,x3,...,x n ); n-dimensional feature vector is used to identify the behavior patterns of different students.
4. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of analyzing the key student behavior parameter features and determining the student behavior analysis result is specifically as follows: For any eigenvector x n As the center of the circle, set the radius to r to form a circular area, and mark the set of all points in this circular area as neighborhood B r (x n );B r (x n )=x p ∈D│dist x n ,x p )≤r}; where dist x n ,x p ) represents x n and x p The distance between them; mark the minimum number of samples in the neighborhood as MinPts; randomly select a point x from x n , judge |B r (x n )|is greater than or equal to MinPts, when|B r (x n )|≥MinPts, then determine x n As a core object, add it to the core set Z; A core object xn is randomly selected from the core set Z, and all points that are density-reachable are added to the new set C1 to form the first critical area of student behavior; where density-reachable is defined as follows: p In x n In the neighborhood of n is a core object, then x p By x n Density direct, if there exists a1,a2,...,a n , where a1 = x n , a n =x p , and a i+1 By a i The density is directly proportional to x p By x n Density can reach; Continue to access the next point in x, repeat the above steps until all points in x are processed, obtain u key student behavior regions, mark the points not included in the key student behavior regions as noise and delete them; the key student behavior regions include u different student behavior regions.
5. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of matching with the preset first database to obtain the student behavior status evaluation result is specifically as follows: Retrieve relevant indexes in the first database according to the key student behavior parameter characteristics of the students to be matched in the key areas of student behavior, select at least one pre-matched student, and form a set of pre-matched students; use each pre-matched student in the set of pre-matched students as a comparison student respectively; Calculate the similarity between the behavioral parameter characteristics of the matching students and the comparison students, including the similarity of action execution accuracy, concentration, student participation, distraction times, and other behavioral characteristics; calculate the similarity of the overall behavioral state of the matching students and the comparison students. The calculation formula is as follows: Where n is the number of behavior feature information types; i is a positive integer from 1 to n; S i is the similarity between the behavior parameter characteristics of the i-th student to be matched and the behavior parameter characteristics of the comparison student; W i For S i The corresponding weight coefficient; S student is the overall behavioral similarity between the students to be matched and the comparison students; If the overall behavior state similarity of student A is greater than the set threshold, it indicates that his performance is good, and output the first regular teaching activity evaluation instruction to maintain the current teaching activity; if the overall behavior state similarity of student A is less than or equal to the set threshold, it indicates that special attention is needed, and output the second special teaching activity evaluation instruction, including increasing individual tutoring, changing teaching methods, and improving participation.
6. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of generating the teaching preparation behavior parameter curve and extracting the key teaching preparation behavior characteristics of the teaching preparation behavior parameter curve is as follows: Convert the discrete teaching preparation behavior parameter curve into a continuous curve, calculate the difference between the teaching preparation behavior parameter curve and the group average curve to obtain a deviation curve; the group average curve refers to the average level of the teacher group; perform interpolation processing on the deviation curve of the teaching preparation behavior parameters to convert it into a continuous deviation curve; Any point between two adjacent points in the deviation curve is on the line connecting these two points. Assuming that the two points are (c1, d1) and (c2, d2), and the interpolation point is (c, d), then Given any c1 < c < c2, by analyzing the above formula, obtain the linear interpolation target value d corresponding to c: The continuous deviation curve of the teaching preparation behavior parameter is sampled at equal intervals, and sampling is performed every time T2 to obtain the m-dimensional feature vector y=(y1, y2, y3, ..., y m ); the m-dimensional feature vector is used to identify different teaching preparation modes.
7. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of analyzing the key teaching preparation behavior parameter characteristics and determining the teaching preparation behavior parameter analysis result is specifically as follows: For any feature vector y m As the center of the circle, set the radius to r to form a circular area, and mark the set of all points in this circular area as neighborhood B r (y m );B r (y m )=y q ∈D│dist(y m ,y q )≤r}; where dist y m ,y q ) represents x n and q The distance between them; the minimum number of samples in the neighborhood is marked as MinPts; Randomly pick a point y from y m , judge |B r (y m )|is greater than or equal to MinPts, when|B r (y m )|≥MinPts, then determine y m As a core object, it is added to the core set Z1; Randomly pick a core object y from the core set Z1 m , add all points that can be reached by its density to the new set C2 to form the first key area of teaching preparation behavior; where the definition of density reachability is as follows: if y q In y m In the neighborhood of m is a core object, then y q By m Density direct, if there exists a1,a2,...,a n , where a1=y m , a n =y q , and a i+1 By a i The density reaches directly, then y q By m Density can reach; Continue to access the next point in y, repeat the above steps until all points in y are processed, obtain v key areas of teaching preparation behavior, mark the points not included in the key areas of teaching preparation behavior as noise and delete them; the key areas of teaching preparation behavior include v different teaching preparation behavior areas.
8. The method for managing physical education activities based on behavior analysis according to claim 1, characterized in that: The process of matching with the preset second database to obtain the teaching preparation behavior parameter state evaluation result is as follows: Obtain at least one teaching preparation behavior parameter characteristic of the teacher to be matched and the teaching preparation behavior parameter characteristics of the comparison teacher; retrieve relevant indexes in the second database according to the teaching preparation behavior parameter characteristics of the teacher to be matched in the key areas of teaching preparation behavior, select at least one pre-matched teacher, and form a set of pre-matched teachers; use each pre-matched teacher in the set of pre-matched teachers as a comparison teacher respectively; Calculate the similarity between the teaching preparation behavior parameter characteristics of the matching teacher and the comparison teacher, including the similarity of teaching explanation clarity, teaching action demonstration accuracy, teaching interaction frequency, teaching resource preparation adequacy, teaching plan execution, and other teaching preparation behavior characteristics; calculate the overall teaching preparation behavior similarity between the matching teacher and the comparison teacher, and the calculation formula is as follows: Where m is the number of behavior parameter feature types prepared for teaching; j is a positive integer from 1 to m; S j is the similarity between the teaching preparation behavior parameter characteristics of the jth matching teacher and the teaching preparation behavior parameter characteristics of the comparison teacher; S teacher The similarity of the overall teaching preparation behavior parameter characteristics between the matched teacher and the comparison teacher; If the overall teaching preparation behavior similarity of teacher B is greater than the set threshold, it indicates that his preparation is sufficient, and output the third regular teaching activity evaluation instruction to maintain the current teaching preparation activity; if the overall teaching preparation behavior similarity of teacher B is less than or equal to the set threshold, it indicates that special attention is needed, and output the fourth special teaching activity evaluation instruction, including increasing lesson preparation time and improving teaching resources.
9. A sports teaching activity management system based on behavior analysis, characterized in that: Used to implement the physical education teaching activity management method based on behavior analysis as claimed in claim 1, the system includes a data acquisition module, a data processing module, a feature extraction module, an analysis and matching module, an instruction output module, a first database, and a second database; the data acquisition module is used to collect student behavior parameters and teaching preparation behavior parameters; the data processing module is used to quantify and integrate parameters, generate student behavior parameter curves and teaching preparation behavior parameter curves; the feature extraction module is used to extract key student behavior parameter features and key teaching preparation behavior features; The analysis and matching module is used to analyze key student behavior parameter characteristics, determine student behavior analysis results, and match them with a preset first database to obtain student behavior status evaluation results, analyze key teaching preparation behavior parameter characteristics, determine teaching preparation behavior parameter analysis results, and match them with a preset second database to obtain teaching preparation behavior parameter status evaluation results; the instruction output module is used to output student behavior analysis evaluation instructions and teaching preparation behavior analysis evaluation instructions; the first database is used to store the corresponding relationship between student behavior analysis results and student behavior status evaluation results; The second database is used to store the corresponding relationship between the teaching preparation behavior analysis results and the teaching preparation behavior status evaluation results.
Citation Information
Patent Citations
A time sequence QAR parameter feature extraction method based on curve interpolation and sampling
CN109948540A
Method for measuring temperature of outer surface of furnace tube of cracking furnace based on density-based spatial clustering of applications with noise (DBSCAN)
CN110398288A
Method for realizing fault detection by using sequential clustering algorithm
CN110826648A
Teaching behavior analysis system for teaching feature fusion and modeling based on knowledge base
CN115239527A
