Teaching evaluation system and evaluation method thereof
By designing the teaching evaluation system and using data collection, screening, analysis and feedback modules, the subjectivity and inconsistency of traditional teaching evaluation methods are solved, the automation and objectivity of teaching evaluation are realized, and the teaching quality is improved.
Patent Information
- Application Number
- CN202411889647.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-05-16
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional teaching evaluation methods have problems such as inconsistent evaluation standards and great influence on subjectivity, and it is difficult to automate and objectify teaching evaluation.
A teaching evaluation system is designed, including a data acquisition module, a data screening module, a student analysis module, a teaching evaluation module and a feedback module. By collecting and screening students' learning data and behavioral data, the teaching evaluation value is calculated, and feedback signals are sent based on the evaluation value.
It realizes the automation and objectivity of teaching evaluation, improves the accuracy of evaluation, helps teachers better understand students' learning situation and teaching effects, and promotes the improvement of teaching quality.
Smart Images
Figure CN120013713A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of higher education technology, and more specifically, to a teaching evaluation system and an evaluation method thereof. Background Art
[0002] Teaching evaluation is an activity that makes value judgments on the teaching process and results based on teaching objectives and serves teaching decision-making. It is a process of judging the actual or potential value of teaching activities. Teaching evaluation is the process of studying the value of teachers' teaching and students' learning. Teaching evaluation generally includes the evaluation of teachers, students, teaching content, teaching methods, teaching environment, and teaching management in the teaching process, but it is mainly the evaluation of teachers' teaching process. The evaluation methods mainly include quantitative evaluation and qualitative evaluation. With the development of information technology, the education industry is also constantly undergoing information reform. As an important link in the education process, teaching evaluation is of great significance to improving teaching quality. The traditional way of evaluating teachers' teaching process mainly relies on students' classroom performance. This method has certain limitations, such as inconsistent evaluation standards and easy to be affected by subjectivity. Therefore, a teaching evaluation system and its evaluation method are proposed here to achieve automated and objective teaching evaluation. Summary of the invention
[0003] To achieve the above object, the present invention provides the following technical solutions:
[0004] A teaching evaluation system, comprising a data collection module, a data screening module, a student analysis module, a teaching evaluation module, and a feedback module;
[0005] The data collection module is used to collect the learning data and first behavior data of students within a preset time period, as well as the second behavior data and evaluation data of students participating in the target teaching content, and then transmit them together to the data screening module;
[0006] The data screening module is used to screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value one, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value one to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value one collected within a preset time period to obtain a type evaluation set;
[0007] The data screening module transmits the credible evaluation set to the teaching evaluation module and transmits the type evaluation set to the student analysis module;
[0008] The student analysis module is used to calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students and send them to the teaching evaluation module;
[0009] The teaching evaluation module establishes a connection between all students’ learning types and credible evaluation sets, calculates based on the results of the connection, obtains the teaching evaluation value, and then transmits the teaching evaluation value to the feedback module;
[0010] The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation values.
[0011] In a preferred embodiment, the student's learning data includes the category of the learning video, the viewing time of the learning video, the progress of the learning video, and the number of learning times.
[0012] In a preferred embodiment, the second behavior data includes completion degree of homework exercises, scores of homework exercises, and interaction frequency.
[0013] In a preferred embodiment, the data screening module is used to screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value 1, retain the evaluation data of the participating students that is greater than or equal to the preset threshold value 1, and summarize the evaluation data to obtain a credible evaluation set, which refers to:
[0014] Step A1, mark the completion degree of after-class exercises in the second behavior data of the students participating in the target teaching content as KHi, the score of after-class exercises as KFi, and the interaction frequency as HDi;
[0015] Step A2, obtaining the preset homework completion standard value b1, homework score standard value b2, interaction frequency standard value b3 in the data screening module, and the proportional coefficients f1, f2, f3 corresponding to the homework completion degree, homework score, and interaction frequency respectively;
[0016] Step A3, calculate the credibility value, KXi = f1*KH i / b1+f2*KFi / b2+f3*HDi / b3, KXi is the credibility value, when the credibility value KXi is greater than or equal to the preset threshold value one, the evaluation data of the participating students will be retained and summarized to obtain a credible evaluation set.
[0017] In a preferred embodiment, the student analysis module is used to calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table into which the type value falls:
[0018] Get the average value of the learning video viewing time PJ1 i, the average value of the learning video progress PJ2 i, and the average value of the learning times PJ3 i of the participating students in different learning video categories within the preset time period, set the average value of the first line of data as XWi, and then set the category of the learning video to LBi, then the type value of the corresponding learning video category In the preset type-division interval table, when all type values LXi fall into their corresponding division intervals, the corresponding learning video category LBi is retained as the learning type of the participating student.
[0019] In a preferred embodiment, the teaching evaluation module establishes a connection between the learning types and the credible evaluation sets of all students, and calculates the teaching evaluation value based on the result of the connection, which means:
[0020] W1. Calculate the influence coefficient Yi of a single student according to the student's learning type, Yi = k1 / (k2+e), k1 is the number of learning types of the participating students that are the same as the category of the target teaching content, k2 is the total number of learning types of the participating students, and e is a natural constant;
[0021] W2. Obtain the evaluation data of a single student and calculate the evaluation value Pi of a single student, Pi = ∑Xi*ti, Xi represents the corresponding evaluation item in the evaluation data, and ti represents the evaluation coefficient corresponding to the evaluation item Xi;
[0022] W3. Establish a connection between the influence coefficient Yi and the evaluation value Pi of the same student, and calculate the connection value Gi, Gi=Pi*(1-Yi);
[0023] W4. Sum up all the connection values Gi and divide it by the total number of participating students that is greater than or equal to the preset threshold value 1 to obtain the teaching evaluation value.
[0024] The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation value:
[0025] The feedback module finds the corresponding feedback signal level according to the teaching evaluation value and the internally preset teaching evaluation value interval - feedback signal level and sends it to the target teacher in the target teaching content.
[0026] In a preferred embodiment, a teaching evaluation method comprises the following steps:
[0027] Step 1: Collect the learning data and first behavior data of students within a preset time period, as well as the second behavior data and evaluation data of students participating in the target teaching content;
[0028] Step 2: Screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value 1, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value 1 to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value 1 within a preset time period to obtain a type evaluation set;
[0029] Step 3: Calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students;
[0030] Step 4: Establish connections between all students' learning types and credible evaluation sets, calculate based on the results of the connections, obtain teaching evaluation values, and then send different levels of feedback signals to the target teachers in the target teaching content based on the teaching evaluation values.
[0031] Technical effects and advantages of the present invention:
[0032] The teaching evaluation platform in the present invention can comprehensively collect students' learning data and behavior data, providing teachers with a basis for a more comprehensive understanding of students' learning situation. Through the data screening module, students with high participation and evaluation data with reference value can be effectively screened out to improve the accuracy of the evaluation. The student analysis module can conduct a more in-depth analysis of students' learning situation based on their learning types, helping teachers to better understand students' learning characteristics and needs. The teaching evaluation module can more accurately evaluate the teaching effect by establishing a connection between the student's influence coefficient and the evaluation value, avoiding the influence of students' subjective factors.
[0033] The feedback module in the present invention can send feedback signals of different levels to the target teachers in the target teaching content according to the teaching evaluation value, helping teachers to adjust teaching methods in time and improve teaching quality, which plays an important role in stimulating teachers' teaching enthusiasm and improving teachers' teaching level. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;
[0035] Figure 1 It is a principle diagram of a teaching evaluation system in the present invention.
[0036] Figure 2 It is a principle diagram of a teaching evaluation method in the present invention. DETAILED DESCRIPTION
[0037] 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.
[0038] Reference Figure 1 - Figure 2 The following examples are obtained:
[0039] Example 1
[0040] A teaching evaluation system comprises a data acquisition module, a data screening module, a student analysis module, a teaching evaluation module and a feedback module; the data acquisition module, the data screening module, the student analysis module, the teaching evaluation module and the feedback module are connected in communication;
[0041] The data collection module is used to collect the learning data and first behavior data of students within a preset time period, as well as the second behavior data and evaluation data of students participating in the target teaching content, and then transmit them together to the data screening module; data collection can be carried out in various ways, such as online questionnaires, student information management systems in the prior art, data interfaces of learning platforms, etc.;
[0042] The data screening module is used to screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value one, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value one to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value one within a preset time period to obtain a type evaluation set; the data screening module transmits the credible evaluation set to the teaching evaluation module, and transmits the type evaluation set to the student analysis module;
[0043] The student analysis module is used to calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students and send them to the teaching evaluation module;
[0044] The teaching evaluation module establishes a connection between all students’ learning types and credible evaluation sets, calculates based on the results of the connection, obtains the teaching evaluation value, and then transmits the teaching evaluation value to the feedback module;
[0045] The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation values. These feedback signals can help teachers understand their strengths and weaknesses in the teaching process, so as to adjust their teaching methods and improve the teaching quality. Feedback can be provided through e-mail, text messages, online chats, etc. to ensure the timeliness and accuracy of the information.
[0046] Students’ learning data include the category of learning videos, the viewing time of learning videos, the progress of learning videos, and the number of learning times.
[0047] The first line of data includes the following:
[0048] Self-explanatory behavior: During the learning process, students try to explain new knowledge or concepts in their own words.
[0049] Questioning behavior: When students encounter questions they do not understand, they take the initiative to ask teachers or classmates for help.
[0050] Summarizing and generalizing behavior: After studying a topic or chapter, students try to summarize and generalize what they have learned in their own words.
[0051] Predictive behavior: Before students learn new knowledge, they try to predict the possible content or results involved.
[0052] Apply knowledge to real-life situations: Students try to apply what they have learned to real life or work to deepen their understanding.
[0053] Collaborative learning with others: Students discuss issues and solve problems with their peers and complete learning tasks together.
[0054] Reflection: Students’ behavior during the learning process, reflecting on and adjusting their learning methods, strategies and results.
[0055] Make study plans: Students make reasonable study plans and schedules based on their learning goals and needs.
[0056] Use of multiple learning resources: Students use a variety of resources such as textbooks, the Internet, and libraries to study and enrich their knowledge system.
[0057] Participation in classroom activities: Students actively participate in classroom discussions, group activities, etc. to improve their learning interest and effectiveness.
[0058] When students have the above behaviors, the total number of their behaviors is counted. For example, student No. 58 only has self-explanation behaviors and participation in classroom activities, then the first behavior data is 2. Assuming that there are two collections of first behavior data within the preset time period, the first time is 2 and the second time is 5, then the average value of his first behavior data XW58 is 3.5.
[0059] The second behavior data includes the completion rate of homework exercises, the scores of homework exercises, and the frequency of interaction.
[0060] The data screening module is used to screen the second behavior data of the students participating in the target teaching content, obtain the credibility value, compare the credibility value with the preset threshold value 1, retain the evaluation data of the participating students that is greater than or equal to the preset threshold value 1, and summarize the evaluation data to obtain the credible evaluation set, which refers to:
[0061] Step A1, mark the completion degree of after-class exercises in the second behavior data of the target teaching content participating students as KHi, the score of after-class exercises as KFi, and the interaction frequency as HDi; i represents the item number, but does not involve the specific content, i=1, 2, 3, 4, ..., q, q is a positive integer, which will not be repeated in the following text;
[0062] Step A2, obtaining the preset homework completion standard value b1, homework score standard value b2, interaction frequency standard value b3 in the data screening module, and the proportional coefficients f1, f2, f3 corresponding to the homework completion degree, homework score, and interaction frequency, respectively; f1, f2, f3 are all greater than zero;
[0063] Step A3, calculate the credibility value, KXi = f1*KHi / b1+f2*KFi / b2+f3*HDi / b3, KXi is the credibility value. When the credibility value KXi is greater than or equal to the preset threshold value one, it indicates that the student's participation in the target teaching content meets the preset requirements, and the evaluation data made by the student has reference value. Otherwise, it has no reference value and can be deleted. The evaluation data of the participating students with reference value will be retained and summarized to obtain a credible evaluation set.
[0064] The student analysis module is used to calculate the type value based on the type evaluation set, and then obtain the student's learning type based on the preset type-division interval table where the type value falls:
[0065] Get the average value of the learning video viewing time PJ1 i, the average value of the learning video progress PJ2 i, and the average value of the learning times PJ3 i of the participating students in different learning video categories within the preset time period, set the average value of the first line of data as XWi, and then set the category of the learning video to LBi, then the type value of the corresponding learning video category In the preset type-division interval table, when all type values LXi fall into their corresponding division intervals, the corresponding learning video category LBi is retained as the learning type of the participating student. l1, l2, and l3 are all specific proportional coefficients and are all greater than zero.
[0066] In actual application, the category of the learning video is set according to the actual situation, and the final learning type of the participating students may be divided into the following learning types:
[0067] Visual learners: These learners understand and remember information through observation and images. They prefer to use visual aids such as charts, images, and videos to help them learn. Visual learners usually have a strong sense of color, shape, and spatial relationships, and are more likely to learn new knowledge through observation and imitation;
[0068] Auditory learners: These learners understand and remember information through listening and speaking. They prefer to acquire knowledge through lectures, discussions, and audio materials. Auditory learners usually have a strong sense of language and sound, and are more likely to learn and understand new concepts through verbal communication and discussion;
[0069] Hands-on learners: These learners understand and remember information through hands-on experience and manipulation. They prefer to learn new knowledge through hands-on experience and practical manipulation. Hands-on learners usually have a strong sense of movement and touch, and are more likely to master skills and concepts through practice and hands-on manipulation;
[0070] Active learners: refers to the learning process that is initiated and led by the learner spontaneously. This type of learner is usually internally driven, they like to ask "why" and are willing to find answers. Their learning behavior is self-driven and they can learn without external promotion. For example, they may take the initiative to participate in discussions, practice or teach others to improve knowledge retention.
[0071] Passive learners: learners learn under external pressure. This type of learners usually rely more on external stimuli, such as pressure from parents, employment pressure, etc., to drive them to learn. Their learning behavior is usually responsive, that is, they learn only when they are required or needed.
[0072] They may be single types of visual learners, auditory learners, hands-on learners, active learners, passive learners, or they may be combined types of learners, such as both visual learners and active learners, or both hands-on learners and active learners.
[0073] The teaching evaluation module establishes a connection between all students’ learning types and credible evaluation sets, and calculates the teaching evaluation value based on the results of the connection. The value is:
[0074] W1. Calculate the influence coefficient Yi of a single student according to the student's learning type, Yi = k1 / (k2+e), k1 is the number of learning types of the participating students that are the same as the category of the target teaching content, k2 is the total number of learning types of the participating students, and e is a natural constant;
[0075] The learning type of the participating student is the same as the category to which the target teaching content belongs, which means: if the category to which the target teaching content belongs belongs to a subcategory of the learning type of the participating student, it can be understood that the learning type of the participating student is a visual learner, who understands and remembers information through observation and images. They like to use visual aids such as charts, images and videos to help them learn. Visual learners are usually familiar with colors, shapes and spatial relationships, and the category to which the target teaching content belongs is geometry science, which is classified as a subcategory of the learning type of the participating student. The corresponding relationship between the two depends on the corresponding relationship set by people in this field in long-term teaching activities, and if the category to which the target teaching content belongs is also simulation animation, which also belongs to a subcategory of the learning type of the participating student, then the number of k1 only needs to be counted once, and no repeated statistics will be performed;
[0076] W2. Obtain the evaluation data of a single student and calculate the evaluation value Pi of a single student, Pi = ∑Xi*ti, Xi represents the corresponding evaluation item in the evaluation data, ti represents the evaluation coefficient corresponding to the evaluation item Xi; if it is conducted through a questionnaire survey, the evaluation data corresponds to four options ABCD, and the evaluation items correspond to different values Xi when the corresponding ABCD are selected. If there is a blank selection, the value of Xi is recorded as zero, and ti represents the evaluation coefficient corresponding to the evaluation item Xi, and ti is a positive integer;
[0077] W3. Establish a connection between the influence coefficient Yi and the evaluation value Pi of the same student, and calculate the connection value Gi, Gi=Pi*(1-Yi); the size of the influence coefficient Yi indicates the influence of students’ subjective factors on the evaluation of the target teaching content. The larger the influence coefficient Yi, the greater the influence of students’ subjective factors, and the lower the fairness of the evaluation of the target teaching content. The larger the evaluation value Pi, the higher the recognition of the target teaching content. After establishing a connection between the influence coefficient Yi and the evaluation value Pi, a fairer evaluation of the target teaching content can be obtained;
[0078] W4. Sum up all the connection values Gi and divide it by the total number of participating students that is greater than or equal to the preset threshold value 1 to obtain the teaching evaluation value.
[0079] The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation value:
[0080] The feedback module finds the corresponding feedback signal level and sends it to the target teacher in the target teaching content according to the teaching evaluation value and its internal preset teaching evaluation value interval - feedback signal level. For example, when the teaching evaluation value is input into the feedback module, it will first be compared with the internal preset teaching evaluation value interval, which usually includes different levels such as excellent, good, general and poor. Then, based on the comparison results, the feedback module will determine the corresponding feedback signal level. If the teaching evaluation value is 90 points, it will be classified as an excellent level. At this time, the feedback module will generate an excellent feedback signal and send it to the target teacher, and encourage the target teacher to continue to maintain an excellent teaching level.
[0081] Example 2
[0082] A teaching evaluation method comprises the following steps:
[0083] Step 1: Collect the students' learning data and first behavior data within a preset time period, as well as the second behavior data and evaluation data of the students who participate in the target teaching content; data collection can be carried out in various ways, such as online questionnaires, student information management systems in the prior art, data interfaces of learning platforms, etc.; students' learning data include the category of learning videos, learning video viewing time, learning video progress, and learning times; second behavior data include completion of after-class exercises, after-class exercise scores, and interaction frequency;
[0084] Step 2: Screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value 1, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value 1 to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value 1 within a preset time period to obtain a type evaluation set;
[0085] Step 3: Calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students; in actual application, the category to which the learning video belongs is set according to the actual situation, which may be a single type of visual learner, auditory learner, hands-on learner, active learner, passive learner, or a combination of multiple types of learners, such as both visual learners and active learners, and both hands-on learners and active learners;
[0086] Step 4. Establish a connection between all students' learning types and credible evaluation sets, calculate according to the results after establishing the connection, obtain the teaching evaluation value, and calculate the connection value Gi, Gi=Pi*(1-Yi); the size of the influence coefficient Yi represents the influence of students' subjective factors on the evaluation of the target teaching content. The larger the influence coefficient Yi, the greater the influence of students on their subjective factors, and the lower the fairness of the evaluation of the target teaching content. The larger the evaluation value Pi, the higher the recognition of the target teaching content. After establishing a connection between the influence coefficient Yi and the evaluation value Pi, a fairer evaluation of the target teaching content can be obtained, and then different levels of feedback signals are sent to the target teachers in the target teaching content according to the teaching evaluation value.
[0087] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0088] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0089] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A teaching evaluation system, characterized in that: It includes data collection module, data screening module, student analysis module, teaching evaluation module and feedback module; The data collection module is used to collect the learning data and first behavior data of students within a preset time period, as well as the second behavior data and evaluation data of students participating in the target teaching content, and then transmit them together to the data screening module; The data screening module is used to screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value one, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value one to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value one collected within a preset time period to obtain a type evaluation set; The data screening module transmits the credible evaluation set to the teaching evaluation module and transmits the type evaluation set to the student analysis module; The student analysis module is used to calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students and send them to the teaching evaluation module; The teaching evaluation module establishes a connection between all students’ learning types and credible evaluation sets, calculates based on the results of the connection, obtains the teaching evaluation value, and then transmits the teaching evaluation value to the feedback module; The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation values.
2. A teaching evaluation system according to claim 1, characterized in that: Students’ learning data include the category of learning videos, the viewing time of learning videos, the progress of learning videos, and the number of learning times.
3. A teaching evaluation system according to claim 2, characterized in that: The second behavior data includes the completion rate of homework exercises, the scores of homework exercises, and the frequency of interaction.
4. A teaching evaluation system according to claim 3, characterized in that: The data screening module is used to screen the second behavior data of the students participating in the target teaching content, obtain the credibility value, compare the credibility value with the preset threshold value 1, retain the evaluation data of the participating students that is greater than or equal to the preset threshold value 1, and summarize the evaluation data to obtain the credible evaluation set, which refers to: Step A1, mark the completion degree of after-class exercises in the second behavior data of the students participating in the target teaching content as KHi, the score of after-class exercises as KFi, and the interaction frequency as HDi; Step A2, obtaining the preset homework completion standard value b1, homework score standard value b2, interaction frequency standard value b3 in the data screening module, and the proportional coefficients f1, f2, f3 corresponding to the homework completion degree, homework score, and interaction frequency respectively; Step A3, calculate the credibility value, KXi = f1*KHi / b1+f2*KFi / b2+f3*HDi / b3, KXi is the credibility value. When the credibility value KXi is greater than or equal to the preset threshold value one, the evaluation data of the participating students will be retained and summarized to obtain a credible evaluation set.
5. A teaching evaluation system according to claim 4, characterized in that: The student analysis module is used to calculate the type value based on the type evaluation set, and then obtain the student's learning type based on the preset type-division interval table where the type value falls: Get the average value of the learning video viewing time PJ1 i, the average value of the learning video progress PJ2 i, and the average value of the learning times PJ3 i of the participating students in different learning video categories within the preset time period, set the average value of the first line of data as XWi, and then set the category of the learning video to LBi, then the type value of the corresponding learning video category In the preset type-division interval table, when all type values LXi fall into their corresponding division intervals, the corresponding learning video category LBi is retained as the learning type of the participating student.
6. A teaching evaluation system according to claim 5, characterized in that: The teaching evaluation module establishes a connection between all students’ learning types and credible evaluation sets, and calculates the teaching evaluation value based on the results of the connection. The value is: W1. Calculate the influence coefficient Yi of a single student according to the student's learning type, Yi = k1 / (k2+e), k1 is the number of learning types of the participating students that are the same as the category of the target teaching content, k2 is the total number of learning types of the participating students, and e is a natural constant; W2. Obtain the evaluation data of a single student and calculate the evaluation value Pi of a single student, Pi = ∑Xi*ti, Xi represents the corresponding evaluation item in the evaluation data, and ti represents the evaluation coefficient corresponding to the evaluation item Xi; W3. Establish a connection between the influence coefficient Yi and the evaluation value Pi of the same student, and calculate the connection value Gi, Gi=Pi*(1-Yi); W4. Sum up all the connection values Gi and divide it by the total number of participating students that is greater than or equal to the preset threshold value 1 to obtain the teaching evaluation value.
7. A teaching evaluation system according to claim 6, characterized in that: The feedback module sends different levels of feedback signals to the target teachers in the target teaching content according to the teaching evaluation value: The feedback module finds the corresponding feedback signal level according to the teaching evaluation value and the internally preset teaching evaluation value interval - feedback signal level and sends it to the target teacher in the target teaching content.
8. A teaching evaluation method according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Collect the learning data and first behavior data of students within a preset time period, as well as the second behavior data and evaluation data of students participating in the target teaching content; Step 2: Screen the second behavior data of the students participating in the target teaching content to obtain a credibility value, compare the credibility value with a preset threshold value 1, retain and summarize the evaluation data of the participating students whose values are greater than or equal to the preset threshold value 1 to obtain a credible evaluation set, and then summarize the learning data and first behavior data of the participating students whose values are greater than or equal to the preset threshold value 1 within a preset time period to obtain a type evaluation set; Step 3: Calculate the type value according to the type evaluation set, and then obtain the student's learning type according to the preset type-division interval table where the type value falls, and then summarize the learning types of all students; Step 4: Establish connections between all students' learning types and credible evaluation sets, calculate based on the results of the connections, obtain teaching evaluation values, and then send different levels of feedback signals to the target teachers in the target teaching content based on the teaching evaluation values.