Teaching quality evaluation method and system based on big data analysis

Abstract

The invention discloses a teaching quality assessment method and system based on big data analysis, and relates to the technical field of teaching quality assessment, and the method comprises the steps: dividing high, medium and low attention regions of students from the teaching data information of a to-be-assessed teacher, judging whether the to-be-assessed teacher depends on the position distribution of the students to carry out the distinguished attention, and if yes, carrying out the assessment. Detecting sight attention conditions of a to-be-evaluated teacher in high, medium and low attention areas of students in the teaching data information, performing preliminary evaluation on three judgment conditions of the teaching quality of the to-be-evaluated teacher to obtain first, second and third types of preliminary evaluation results, presetting a historical extraction detection time period, and performing statistics to obtain an auxiliary detection preliminary evaluation result set; and comprehensively evaluating the teaching quality of the to-be-evaluated teacher under two conditions according to the category numbers of the first, second and third categories of initial evaluation results contained in the auxiliary test initial evaluation result set. According to the teaching quality evaluation method and system based on big data analysis, the efficiency of teaching quality evaluation work can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of teaching quality assessment, and in particular to a teaching quality assessment method and system based on big data analysis. Background Art

[0002] Teaching quality assessment aims to provide a more comprehensive, objective and scientific education quality evaluation system. Through big data analysis, educators can more accurately understand students' learning situation, teachers' teaching effect and the use of educational resources, so as to make more reasonable educational decisions.

[0003] With the development of informatization, informatization can be used to evaluate the fairness of teachers' classroom teaching. For example, the teaching quality evaluation device obtains multiple teaching images, and determines the teacher's line of sight by analyzing the direction of the teacher's head in each teaching image, so as to evaluate the teacher's attention to different areas in the classroom. However, this evaluation method is not perfect because it only takes into account the teacher's teaching status, and does not conduct a correlation analysis of the student's listening status. In addition, the factors analyzed are relatively simple, resulting in low accuracy of the final teaching quality evaluation results and failure to fully utilize resource data information. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a teaching quality evaluation method and system based on big data analysis.

[0005] In a first aspect, the present application provides a teaching quality assessment method based on big data analysis, the method comprising:

[0006] Select a teacher to be evaluated who needs to be evaluated for teaching quality, collect the teaching data information of the teacher to be evaluated, divide the student high attention area, the student medium attention area and the student low attention area from the teaching data information, if it is determined that the teacher to be evaluated does not rely on the student position distribution for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when they are located in the student high attention area, the student medium attention area and the student low attention area, then conduct a preliminary evaluation on the teaching quality of the teacher to be evaluated to obtain a first type of preliminary evaluation result;

[0007] If it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the eye contact attention of the teacher to be evaluated in the teaching data information is divided into teacher high attention, teacher medium attention and teacher low attention, wherein the teacher high attention is in the student high attention area, the teacher medium attention is in the student medium attention area, and the teacher low attention is in the student low attention area, a preliminary evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a second type of preliminary evaluation result;

[0008] If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a third type of preliminary evaluation result;

[0009] A historical extraction detection period is preset, and according to the historical extraction detection period, a set of auxiliary test initial evaluation results is statistically obtained. If the set of auxiliary test initial evaluation results contains one of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result;

[0010] If the auxiliary test initial evaluation result set contains at least two types of initial evaluation results among the first type of initial evaluation results, the second type of initial evaluation results and the third type of initial evaluation results, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

[0011] Preferably, selecting teachers to be evaluated who need to undergo teaching quality evaluation, and collecting teaching data information of the teachers to be evaluated based on the teachers to be evaluated;

[0012] Preset the first detection period and the second detection period, divide the distribution areas of students with different attention levels in the first detection period from the teaching data information, and output the student high attention area, the student medium attention area and the student low attention area;

[0013] If it is determined that the teacher to be evaluated does not rely on the distribution of student positions for differential attention, then the first type of evaluation situation 1 is output;

[0014] According to the first type of evaluation situation 1, if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when the teacher is located in the student high attention area, the student medium attention area and the student low attention area respectively, then the first type of evaluation situation 2 is output;

[0015] According to the first type of evaluation situation 2, extract the student and teacher attention data belonging to the first detection period from the teaching data information, and output the first type of preprocessing feature data 1;

[0016] According to the second detection period and the first type of evaluation situation 2, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the first type of preprocessing feature data 2;

[0017] The first type of preprocessed feature data 1 and the first type of preprocessed feature data 2 are combined into the first type of pre-evaluation data;

[0018] Based on the first type of pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the first type of initial evaluation results.

[0019] Preferably, if it is determined that the teacher to be evaluated relies on the distribution of student positions for differential attention, the second type of evaluation situation 1 is output;

[0020] According to the second type of evaluation situation 1, if it is detected that the eye contact of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, among which the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, then the second type of evaluation situation 2 is output;

[0021] According to the second type of evaluation situation 1, extract the student and teacher attention data belonging to the first detection period from the teaching data information, and output the second type of preprocessing feature data 1;

[0022] According to the second detection period and the second type of evaluation situation 2, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the second type of preprocessing feature data 2;

[0023] The second type of preprocessed feature data one and the second type of preprocessed feature data two are combined into the second type of pre-evaluation data;

[0024] Based on the second type of pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teachers to be evaluated to obtain the second type of initial evaluation results.

[0025] Preferably, if the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, then the second type of evaluation situation three is output;

[0026] According to the second detection period and the second type of evaluation situation three, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the second type of preprocessing feature data three;

[0027] The second type of pre-processed feature data one and the second type of pre-processed feature data three are combined into the third type of pre-evaluation data;

[0028] Based on the third category pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the third category initial evaluation result.

[0029] Preferably, a history extraction detection period is preset, and all history teaching data of the teacher to be evaluated within the history extraction detection period are counted;

[0030] Conducting a preliminary evaluation of the teaching quality of all the history teaching data to obtain a preliminary evaluation result set of the auxiliary test;

[0031] If the auxiliary test initial evaluation result set contains one of the first category of initial evaluation results, the second category of initial evaluation results and the third category of initial evaluation results, then based on the auxiliary test initial evaluation result set, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result.

[0032] Preferably, if the auxiliary test preliminary evaluation result set contains at least two of the first type of preliminary evaluation results, the second type of preliminary evaluation results and the third type of preliminary evaluation results, then the temporal connectivity between the three types of preliminary evaluation results or the two types of preliminary evaluation results in the auxiliary test preliminary evaluation result set is statistically analyzed to obtain the temporal connectivity influencing factor;

[0033] According to the timing connection influencing factors and the auxiliary test initial evaluation result set, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

[0034] Second, a teaching quality evaluation system based on big data analysis, including:

[0035] The first preliminary evaluation module is used to select teachers to be evaluated who need to be evaluated for teaching quality, collect teaching data information of the teachers to be evaluated, and divide the students' high attention area, students' medium attention area and students' low attention area from the teaching data information. If it is judged that the teachers to be evaluated do not rely on the students' position distribution for differentiated attention, and if it is detected that the sight attention of the teachers to be evaluated in the teaching data information is the same when they are located in the students' high attention area, students' medium attention area and students' low attention area, a preliminary evaluation is performed on the teaching quality of the teachers to be evaluated to obtain the first type of preliminary evaluation results;

[0036] The second preliminary evaluation module is used for, if it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, wherein the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, then a preliminary evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a second type of preliminary evaluation result;

[0037] The third preliminary evaluation module is used to determine if the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, and to conduct a preliminary evaluation of the teaching quality of the teacher to be evaluated to obtain the third type of preliminary evaluation results;

[0038] The first comprehensive evaluation module is used to preset a historical extraction detection period, and obtain a set of auxiliary test initial evaluation results according to the historical extraction detection period. If the auxiliary test initial evaluation result set contains one of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result;

[0039] The second comprehensive evaluation module is used to determine if the auxiliary test initial evaluation result set contains at least two types of initial evaluation results from the first type of initial evaluation results, the second type of initial evaluation results and the third type of initial evaluation results, and to conduct a comprehensive evaluation on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

[0040] Compared with the prior art, the present invention has the following characteristics and beneficial effects:

[0041] By first judging the teaching habits of the teachers to be evaluated, that is, whether they rely on the distribution of students' positions to differentiate their attention, the conditions directly affect the evaluation of the teachers' teaching quality, and will also have a direct impact on the subsequent students' attention. The teaching data information of the teachers to be evaluated is extracted based on the results of multi-condition judgments, so as to refine the extraction of diversified data information, that is, to conduct targeted comparative analysis of data information of the same category, so as to reduce the greater interference between each other caused by the unified processing of diversified data information, and even the greater error of the final analysis result, and then further divide the students into three areas of high, medium and low attention, and divide the divided The regional results and the teacher's line of sight attention in these three areas are tested and counted, and finally the matching conditions of the students' and teachers' attention conditions are further judged to determine two situations, and then the corresponding feature data are extracted from the teaching data information according to the two judged situations. Through the above processing method, the orderliness of the entire teaching quality evaluation and analysis process is improved, and the utilization rate of resource data information is improved. The influencing factors of teachers and students are taken into consideration more comprehensively, and differentiated conditional judgments are made, as well as the data between the two are combined for analysis, so as to realize indirect verification of the final teaching quality evaluation results, and improve the efficiency and accuracy of teaching quality evaluation work as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of the steps of a teaching quality evaluation method based on big data analysis mainly embodied in this embodiment.

[0043] Figure 2 It is a structural block diagram of a teaching quality evaluation system based on big data analysis mainly embodied in this embodiment. DETAILED DESCRIPTION

[0044] The present invention is further described in detail below in conjunction with the following examples.

[0045] Reference Figure 1 , a teaching quality evaluation method based on big data analysis, the method comprises the following steps:

[0046] S1. Select teachers to be evaluated whose teaching quality needs to be evaluated, collect the teaching data information of the teachers to be evaluated, divide the teaching data information into student high attention area, student medium attention area and student low attention area, if it is judged that the teachers to be evaluated do not rely on the students' position distribution to distinguish attention, and if it is detected that the sight attention of the teachers to be evaluated in the teaching data information is the same when they are respectively located in the student high attention area, student medium attention area and student low attention area, then conduct a preliminary evaluation on the teaching quality of the teachers to be evaluated to obtain the first type of preliminary evaluation results.

[0047] S2. If it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the eye contact attention of the teacher to be evaluated in the teaching data information is divided into teacher high attention, teacher medium attention and teacher low attention, among which the teacher high attention is in the student high attention area, the teacher medium attention is in the student medium attention area, and the teacher low attention is in the student low attention area, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the second type of preliminary evaluation result.

[0048] S3. If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, a preliminary evaluation of the teaching quality of the teacher to be evaluated is conducted to obtain the third type of preliminary evaluation result.

[0049] S4. Preset a historical extraction detection period, and obtain the auxiliary test initial evaluation result set based on the historical extraction detection period. If the auxiliary test initial evaluation result set contains one of the first category of initial evaluation results, the second category of initial evaluation results, and the third category of initial evaluation results, conduct a comprehensive evaluation on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result.

[0050] S5. If the auxiliary test initial evaluation result set contains at least two types of initial evaluation results among the first type of initial evaluation results, the second type of initial evaluation results and the third type of initial evaluation results, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

[0051] Specifically, by first judging the teaching habits of the teachers to be evaluated, that is, whether they rely on the distribution of students' positions to distinguish attention, the conditions directly affect the evaluation of the teachers' teaching quality, and will also have a direct impact on the subsequent students' attention. The teaching data information of the teachers to be evaluated is extracted based on the results of multi-condition judgments to extract feature data, so as to refine the extraction of diversified data information, that is, to conduct targeted comparative analysis of data information of the same category, so as to reduce the greater interference between each other caused by the unified processing of diversified data information, and even the greater error in the final analysis result, and further divide the students into three attention areas of high, medium and low, and The divided area results and the teacher's line of sight attention in these three areas are tested and statistically analyzed, and finally the matching conditions of the students' and teachers' attention conditions are further judged to determine two situations, and then the corresponding feature data are extracted from the teaching data information according to the two judged situations. Through the above processing method, the orderliness of the entire teaching quality evaluation and analysis process is improved, and the utilization rate of resource data information is improved. The influencing factors of teachers and students are taken into consideration more comprehensively, and differentiated conditional judgments are made, as well as the data between the two are combined for analysis, so as to realize indirect verification of the final teaching quality evaluation results, and improve the efficiency and accuracy of teaching quality evaluation work as a whole.

[0052] The specific step S1 includes the following sub-steps:

[0053] Select teachers who need to be evaluated for teaching quality, and collect their teaching data information based on the teachers.

[0054] A first detection period and a second detection period are preset, and distribution areas of students with different attention levels in the first detection period are divided from the teaching data information, and the student high attention area, student medium attention area and student low attention area are output.

[0055] If it is determined that the teacher to be evaluated does not rely on the distribution of student positions for differential attention, the first type of evaluation situation one is output.

[0056] According to the first type of evaluation situation one, if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when they are located in the students' high attention area, the students' medium attention area and the students' low attention area, then the first type of evaluation situation two is output.

[0057] According to the first type of evaluation situation two, the student and teacher attention data belonging to the first detection period are extracted from the teaching data information, and the first type of preprocessing feature data one is output.

[0058] According to the second detection period and the first type of evaluation situation two, the student and teacher attention data belonging to the second detection period are extracted from the teaching data information, and the first type of preprocessing feature data two is output.

[0059] The first type of preprocessing feature data 1 and the first type of preprocessing feature data 2 are combined into the first type of pre-evaluation data.

[0060] Based on the first type of pre-evaluation data, a preliminary evaluation of the teaching quality of the teachers to be evaluated is conducted to obtain the first type of initial evaluation results.

[0061] Specifically, such as teaching data information (referring to all characteristic data information of the teacher to be evaluated in the previous class, including: students' class data, teachers' own teaching data and other types of data information), the first detection period and the second detection period (such as the first detection period is: 10 minutes before the teacher to be evaluated starts the class. During this time, the distribution of students' eye contact can be detected, whether they are highly focused or scattered in class. The second detection period is: the time period between the last 10 minutes after the teacher to be evaluated finishes a class and the 10 minutes after the teacher to be evaluated starts the class. Because in the last 10 minutes after the teacher to be evaluated finishes a class, students are generally more anxious and their attention to the class changes greatly, so in the first detection period The student class data information for the remaining time after the second detection period is highly disruptive, so no major analysis will be conducted subsequently. The subsequent analysis will focus on the class teaching data information within the second detection period), student high attention area, student medium attention area and student low attention area (such as dividing the student position area in the entire classroom into three parts: area A, area B, and area C, among which the students in area A have the highest visual attention in class (for example, there are 30 students in area A, and 25 of them are listening carefully, then the student attention in area A is about 83%), then area A is the student high attention area, and so on, if the students in area B have medium visual attention in class, then area B is the student medium attention area, and if the students in area C have low visual attention, then area A is the student high attention area. The first type of evaluation situation one (meaning that the teacher to be evaluated will not pay more attention to a certain group of students just because they listen to the class most attentively), the first type of evaluation situation two (such as the teacher's gaze stays in areas A, B, and C with the same degree of attention during the lecture, then the judgment result is the first type of evaluation situation two, which is also a further verification of the first type of evaluation situation one), the first type of preprocessed feature data one (such as extracting the student attention data in areas A, B, and C 10 minutes before the class starts, as well as the teacher's gaze attention data from the teaching data information. The teacher's gaze attention data here is relatively Similarly, the attention data of students and teachers 10 minutes after the class is completed are grouped as the first type of preprocessed feature data one), the first type of preprocessed feature data two (similarly, the student attention data of areas A, B, and C in the last 10 minutes after the teacher to be evaluated finishes the class and the 10 minutes after the teacher to be evaluated starts the class are extracted from the teaching data information, as well as the teacher's line of sight attention data. The teacher's line of sight attention data here is also the same in areas A, B, and C. The student and teacher attention data in this second detection period are grouped as the first type of preprocessed feature data two), the first type of initial evaluation results (that is, based on the data information obtained from the above statistics, a preliminary teaching quality evaluation of the teacher to be evaluated is performed,This evaluation process can use the existing machine vision-based concentration analysis and evaluation system: this system usually uses face recognition technology to obtain students' facial features and uses algorithms to determine the students' concentration in class. Although it mainly focuses on students' concentration, similar technologies can also be used to monitor teachers' sight and behavior, thereby indirectly evaluating teachers' teaching input and effectiveness. If the first-class initial evaluation result is 85%-90%, it is the second level).

[0062] The specific step S2 includes the following sub-steps:

[0063] If it is determined that the teacher to be evaluated relies on the distribution of students' positions for differential attention, then the second type of evaluation situation one is output.

[0064] According to the second type of evaluation situation one, if it is detected that the eye contact attention of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, among which the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, then the second type of evaluation situation two is output.

[0065] According to the second type of evaluation situation one, the student and teacher attention data belonging to the first detection period are extracted from the teaching data information, and the second type of preprocessing feature data one is output.

[0066] According to the second detection period and the second type of evaluation situation 2, the student and teacher attention data belonging to the second detection period are extracted from the teaching data information, and the second type of preprocessing feature data 2 is output.

[0067] The second type of preprocessing feature data one and the second type of preprocessing feature data two are combined into the second type of pre-evaluation data.

[0068] Based on the second type of pre-evaluation data, a preliminary evaluation of the teaching quality of the teachers to be evaluated is conducted to obtain the second type of initial evaluation results.

[0069] Specifically, for example, the second type of evaluation situation 1 (referring to which part of the students the teacher to be evaluated listens to the class most attentively, so he will pay more attention to that part of the students), the second type of evaluation situation 2 (for example, the degree of attention of the teacher's gaze in the three areas A, B, and C is different, and the frequency and duration of the teacher's gaze attention in area A, area B, and area C are extracted from the teaching data information, and the situation where the teacher's gaze attention falls in the three areas A, B, and C is divided, that is, if the teacher's high attention is a1, the teacher's medium attention is b1, and the teacher's low attention is c1, if the student's high attention is a2, the student's medium attention is b2, and the student's low attention is c2, And the teacher's high attention falls in area A: a1-a2, the teacher's medium attention falls in area B: b1-b2, and the teacher's low attention falls in area C: c1-c2, then the judgment result is the second category evaluation situation two, which is also a further verification of the second category evaluation situation one), the second category preprocessing feature data one, the second category preprocessing feature data two (the explanations are the same as the first category preprocessing feature data one and the first category preprocessing feature data two, and no further explanation is given here. It should be noted that the teacher's visual attention here is divided into high, medium and low), the second category initial evaluation results (the explanation is the same as the first category initial evaluation results, and no further explanation is given here. If the second category initial evaluation results are 80%-85%, it is the third level).

[0070] The specific step S3 includes the following sub-steps:

[0071] If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, then the second type of evaluation situation three is output.

[0072] According to the second detection period and the second type of evaluation situation three, the student and teacher attention data belonging to the second detection period are extracted from the teaching data information, and the second type of preprocessing feature data three is output.

[0073] The second type of preprocessing feature data one and the second type of preprocessing feature data three are combined to form the third type of pre-evaluation data.

[0074] Based on the third category pre-evaluation data, a preliminary evaluation of the teaching quality of the teachers to be evaluated is conducted to obtain the third category preliminary evaluation results.

[0075] Specifically, if the second type of evaluation situation three is judged under the conditions of the second type of evaluation situation one (for example, the degree of attention of the teacher's gaze when lecturing in the three areas A, B, and C is different, and the teacher's high attention falls in area A: a1-c2, the teacher's medium attention falls in area B: b1-b2, and the teacher's low attention falls in area C: c1-a2, then the judgment result is the second type of evaluation situation three, which is also a further verification of the second type of evaluation situation one), the second type of preprocessing feature data three (the explanation is the same as the first type of preprocessing feature data two, and no further explanation is given here. It should be noted that the teacher's gaze attention here is divided into high, medium, and low), the third type of initial evaluation results (the explanation is the same as the first type of initial evaluation results, and no further explanation is given here. If the third type of initial evaluation results is 90%-95%, it is the first level. It should be noted that the first level, the second level, and the third level are downgraded in turn).

[0076] The specific step S4 includes the following sub-steps:

[0077] A history extraction and testing period is preset, and all history teaching data of the teacher to be evaluated within the history extraction and testing period are counted.

[0078] A preliminary evaluation of the teaching quality of all history course teaching data was conducted to obtain a set of preliminary evaluation results for the auxiliary test.

[0079] If the auxiliary test initial evaluation result set contains one of the first, second and third types of initial evaluation results, then a comprehensive evaluation of the teaching quality of the teacher to be evaluated is conducted based on the auxiliary test initial evaluation result set to obtain a first comprehensive evaluation result.

[0080] Specifically, such as the history extraction detection time period (that is, extracting the most recent history class teaching data information from all the history class teaching data information of the teacher to be evaluated: if the history class teaching data information of the previous month is extracted for subsequent analysis), the auxiliary test initial evaluation result set (if the teacher to be evaluated has 20 classes in the previous month, the history class teaching data information of each class will be evaluated for teaching quality, and all the teaching quality evaluation results of the evaluation will be combined to obtain the auxiliary test initial evaluation result set. It should be noted that this evaluation process is the same as the first, second and third types of initial evaluation results), the first comprehensive evaluation result (if the 20 initial evaluation results in the auxiliary test initial evaluation result set are all the first type of initial evaluation results, the second type of initial evaluation results or the third type of initial evaluation results, it can be explained that the teaching quality of the evaluated teacher has remained unchanged and has not been improved or reduced. Then the 20 initial evaluation results are averaged to obtain the first comprehensive evaluation result).

[0081] The specific step S5 includes the following sub-steps:

[0082] If the auxiliary test preliminary evaluation result set contains at least two of the first category, the second category and the third category, the temporal connectivity between the three categories or two categories of preliminary evaluation results in the auxiliary test preliminary evaluation result set is statistically analyzed to obtain the temporal connectivity influencing factor.

[0083] According to the temporal connection influencing factors and the initial evaluation result set of the auxiliary test, a comprehensive evaluation is conducted on the teaching quality of the teachers to be evaluated to obtain the second comprehensive evaluation result.

[0084] Specifically, for example, the temporal connection influencing factor (if the 20 preliminary evaluation results in the auxiliary test preliminary evaluation result set simultaneously include the first type of preliminary evaluation results, the second type of preliminary evaluation results, or simultaneously include the first type of preliminary evaluation results, the third type of preliminary evaluation results, or simultaneously include the second type of preliminary evaluation results, the third type of preliminary evaluation results, or simultaneously include the first type of preliminary evaluation results, the second type of preliminary evaluation results, and the third type of preliminary evaluation results, then the temporal connection between the two types of preliminary evaluation results or the three types of preliminary evaluation results contained therein is statistically analyzed. For example, if there are three types of preliminary evaluation results, and these three types of preliminary evaluation results The position relationship in time sequence is that the first 10 preliminary evaluation results are the first category of preliminary evaluation results, the middle 5 preliminary evaluation results are the third category of preliminary evaluation results, and the last 5 preliminary evaluation results are the second category of preliminary evaluation results. The third category of preliminary evaluation results is taken as the starting analysis target, because the third category of preliminary evaluation results has the highest quality and is the subsequent development target. The time sequence connectivity of the third category of preliminary evaluation results is 15 / 20=75%. Finally, if the average value of the 20 preliminary evaluation results is P1, and if P1*75% is P2, then the second comprehensive evaluation result is P2: including the teaching quality evaluation value and grade).

[0085] A teaching quality evaluation system based on big data analysis, by applying a teaching quality evaluation method based on big data analysis as described above, including preliminary evaluation module one, preliminary evaluation module two, preliminary evaluation module three, first comprehensive evaluation module and second comprehensive evaluation module, with reference to Figure 2, through the initial evaluation module one, select the teacher to be evaluated who needs to be evaluated for teaching quality, collect the teaching data information of the teacher to be evaluated, divide the student high attention area, the student medium attention area and the student low attention area from the teaching data information, if it is judged that the teacher to be evaluated does not rely on the student position distribution to distinguish attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when they are located in the student high attention area, the student medium attention area and the student low attention area, then the teaching quality of the teacher to be evaluated is preliminarily evaluated to obtain the first type of initial evaluation results; through the initial evaluation module two, if it is judged that the teacher to be evaluated relies on the student position distribution to distinguish attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is divided into teacher high attention, teacher medium attention and teacher low attention, among which the teacher high attention is in the student high attention area, the teacher medium attention is in the student medium attention area, and the teacher low attention is in the student low attention area, then the teaching quality of the teacher to be evaluated is preliminarily evaluated to obtain the first type of initial evaluation results. A preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the second type of preliminary evaluation result; through the preliminary evaluation module three, it is judged that if the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the third type of preliminary evaluation result; through the first comprehensive evaluation module, a historical extraction detection period is preset, and according to the historical extraction detection period, a set of auxiliary test preliminary evaluation results is statistically obtained. If the auxiliary test preliminary evaluation result set contains one of the first type of preliminary evaluation results, the second type of preliminary evaluation results and the third type of preliminary evaluation results, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the first comprehensive evaluation result; through the second comprehensive evaluation module, it is judged that if the auxiliary test preliminary evaluation result set contains at least two types of preliminary evaluation results among the first type of preliminary evaluation results, the second type of preliminary evaluation results and the third type of preliminary evaluation results, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the second comprehensive evaluation result.

[0086] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A teaching quality evaluation method based on big data analysis, characterized in that: The following steps are involved: Select a teacher to be evaluated who needs to be evaluated for teaching quality, collect the teaching data information of the teacher to be evaluated, divide the student high attention area, the student medium attention area and the student low attention area from the teaching data information, if it is determined that the teacher to be evaluated does not rely on the student position distribution for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when they are located in the student high attention area, the student medium attention area and the student low attention area, then conduct a preliminary evaluation on the teaching quality of the teacher to be evaluated to obtain a first type of preliminary evaluation result; If it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the eye contact attention of the teacher to be evaluated in the teaching data information is divided into teacher high attention, teacher medium attention and teacher low attention, wherein the teacher high attention is in the student high attention area, the teacher medium attention is in the student medium attention area, and the teacher low attention is in the student low attention area, a preliminary evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a second type of preliminary evaluation result; If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a third type of preliminary evaluation result; A historical extraction detection period is preset, and according to the historical extraction detection period, a set of auxiliary test initial evaluation results is statistically obtained. If the set of auxiliary test initial evaluation results contains one of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result; If the auxiliary test initial evaluation result set contains at least two types of initial evaluation results among the first type of initial evaluation results, the second type of initial evaluation results and the third type of initial evaluation results, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

2. According to the teaching quality evaluation method based on big data analysis according to claim 1, it is characterized in that: A teacher to be evaluated who needs to be evaluated for teaching quality is selected, and teaching data information of the teacher to be evaluated is collected. A student high attention area, a student medium attention area, and a student low attention area are divided from the teaching data information. If it is determined that the teacher to be evaluated does not rely on the student position distribution for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when they are located in the student high attention area, the student medium attention area, and the student low attention area, a preliminary evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first type of preliminary evaluation result, which is specifically as follows: Selecting teachers to be evaluated who need to undergo teaching quality evaluation, and collecting teaching data information of the teachers to be evaluated; Preset the first detection period and the second detection period, divide the distribution areas of students with different attention levels in the first detection period from the teaching data information, and output the student high attention area, the student medium attention area and the student low attention area; If it is determined that the teacher to be evaluated does not rely on the distribution of student positions for differential attention, then the first type of evaluation situation 1 is output; According to the first type of evaluation situation 1, if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is the same when the teacher is located in the student high attention area, the student medium attention area and the student low attention area respectively, then the first type of evaluation situation 2 is output; According to the first type of evaluation situation 2, extract the student and teacher attention data belonging to the first detection period from the teaching data information, and output the first type of preprocessing feature data 1; According to the second detection period and the first type of evaluation situation 2, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the first type of preprocessing feature data 2; The first type of preprocessed feature data 1 and the first type of preprocessed feature data 2 are combined into the first type of pre-evaluation data; Based on the first type of pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the first type of initial evaluation results.

3. According to claim 2, a teaching quality evaluation method based on big data analysis is characterized in that: If it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, wherein the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, the steps of performing a preliminary evaluation on the teaching quality of the teacher to be evaluated to obtain the second type of preliminary evaluation results are specifically as follows: If it is judged that the teacher to be evaluated relies on the distribution of students' positions for differential attention, the second type of evaluation situation 1 is output; According to the second type of evaluation situation 1, if it is detected that the eye contact of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, among which the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, then the second type of evaluation situation 2 is output; According to the second type of evaluation situation 1, extract the student and teacher attention data belonging to the first detection period from the teaching data information, and output the second type of preprocessing feature data 1; According to the second detection period and the second type of evaluation situation 2, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the second type of preprocessing feature data 2; The second type of preprocessed feature data one and the second type of preprocessed feature data two are combined into the second type of pre-evaluation data; Based on the second type of pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teachers to be evaluated to obtain the second type of initial evaluation results.

4. According to claim 3, a teaching quality evaluation method based on big data analysis is characterized in that: If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, the steps of conducting a preliminary evaluation on the teaching quality of the teacher to be evaluated to obtain the third type of preliminary evaluation results are specifically as follows: If the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, then the second type of evaluation situation three is output; According to the second detection period and the second type of evaluation situation three, extract the student and teacher attention data belonging to the second detection period from the teaching data information, and output the second type of preprocessing feature data three; The second type of pre-processed feature data one and the second type of pre-processed feature data three are combined into the third type of pre-evaluation data; Based on the third category pre-evaluation data, a preliminary evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain the third category initial evaluation result.

5. According to claim 4, a teaching quality evaluation method based on big data analysis is characterized in that: A historical extraction detection period is preset, and according to the historical extraction detection period, a set of auxiliary test initial evaluation results is obtained by statistics. If the set of auxiliary test initial evaluation results contains one of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, a step of comprehensively evaluating the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result is specifically as follows: Preset the history extraction test period and collect statistics on all history teaching data of the teacher to be evaluated during the history extraction test period; Conducting a preliminary evaluation of the teaching quality of all the history teaching data to obtain a preliminary evaluation result set of the auxiliary test; If the auxiliary test initial evaluation result set contains one of the first category of initial evaluation results, the second category of initial evaluation results and the third category of initial evaluation results, then based on the auxiliary test initial evaluation result set, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result.

6. A teaching quality evaluation method based on big data analysis according to claim 5, characterized in that: If the auxiliary test initial evaluation result set contains at least two of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, the steps of comprehensively evaluating the teaching quality of the teacher to be evaluated to obtain the second comprehensive evaluation result are specifically as follows: If the auxiliary test preliminary evaluation result set contains at least two of the first type of preliminary evaluation results, the second type of preliminary evaluation results and the third type of preliminary evaluation results, the temporal connectivity between the three types of preliminary evaluation results or the two types of preliminary evaluation results in the auxiliary test preliminary evaluation result set is calculated to obtain the temporal connectivity impact factor; According to the timing connection influencing factors and the auxiliary test initial evaluation result set, a comprehensive evaluation is conducted on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

7. A teaching quality evaluation system based on big data analysis, characterized in that: The system is used to implement a teaching quality evaluation method based on big data analysis as described in any one of claims 1 to 6, comprising: The first preliminary evaluation module is used to select teachers to be evaluated who need to be evaluated for teaching quality, collect teaching data information of the teachers to be evaluated, and divide the students' high attention area, students' medium attention area and students' low attention area from the teaching data information. If it is judged that the teachers to be evaluated do not rely on the students' position distribution for differentiated attention, and if it is detected that the sight attention of the teachers to be evaluated in the teaching data information is the same when they are located in the students' high attention area, students' medium attention area and students' low attention area, a preliminary evaluation is performed on the teaching quality of the teachers to be evaluated to obtain the first type of preliminary evaluation results; The second preliminary evaluation module is used for, if it is determined that the teacher to be evaluated relies on the position distribution of students for differentiated attention, and if it is detected that the sight attention of the teacher to be evaluated in the teaching data information is divided into high teacher attention, medium teacher attention and low teacher attention, wherein the high teacher attention is in the high student attention area, the medium teacher attention is in the medium student attention area, and the low teacher attention is in the low student attention area, then a preliminary evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a second type of preliminary evaluation result; The third preliminary evaluation module is used to determine if the teacher's high attention is in the student's low attention area, the teacher's medium attention is in the student's medium attention area, and the teacher's low attention is in the student's high attention area, and to conduct a preliminary evaluation of the teaching quality of the teacher to be evaluated to obtain the third type of preliminary evaluation results; The first comprehensive evaluation module is used to preset a historical extraction detection period, and obtain a set of auxiliary test initial evaluation results according to the historical extraction detection period. If the auxiliary test initial evaluation result set contains one of the first type of initial evaluation results, the second type of initial evaluation results, and the third type of initial evaluation results, a comprehensive evaluation is performed on the teaching quality of the teacher to be evaluated to obtain a first comprehensive evaluation result; The second comprehensive evaluation module is used to determine if the auxiliary test initial evaluation result set contains at least two types of initial evaluation results from the first type of initial evaluation results, the second type of initial evaluation results and the third type of initial evaluation results, and to conduct a comprehensive evaluation on the teaching quality of the teacher to be evaluated to obtain a second comprehensive evaluation result.

Images