Ideological and political teaching model using fuzzy analytic hierarchy process based on machine learning and artificial intelligence

Abstract

Ideological and political education plays an important role in supporting social talent input. However, the current evaluation effect of ideological and political education is difficult to quantify. Therefore, in order to improve the evaluation effect of ideological and political education, based on artificial intelligence algorithms, this study combines machine learning ideas and the current status of ideological and political education to build a fuzzy analytic hierarchy process model of the of ideological and political teaching quality based on machine learning and artificial intelligence. Moreover, this study uses a three-tier structure to build a model network structure, and based on the characteristics of fuzzy evaluation, this study uses the expert system to conduct data management, operation and control of model evaluation, and build a corresponding database to update the data in real time. In addition, in order to verify the effect of the model, this study sets simulation experiments to analyze the model performance. From the point of view of running effect and running speed, this research model meets the actual needs of the system, so it can be applied to the evaluation process of ideological and political teaching quality in colleges and universities.

Keywords

Machine learning ideological and political education teaching quality fuzzy AHP model

1 Introduction

With the deepening of the reform of the new ideological and political curriculum standards, from teaching concepts, curriculum structure settings, textbook content changes to teaching form design, are all impacting and changing the traditional ideological and political classrooms and affecting the learning and daily life of students. However, the deficiencies and shortcomings of the existing classroom teaching evaluation have gradually emerged: the final teaching evaluation with teacher as the center and with exam selection as the final purpose not only hinders the growth of teachers, affects the independent growth and comprehensive development of students, but also seriously hinders the further deepening of ideological and political curriculum reform. Therefore, how to scientifically and effectively carry out ideological and political classroom teaching evaluation and promote the implementation of the core quality of the discipline through the reform of classroom teaching evaluation to make the classroom teaching evaluation activities not only highlight the comprehensive development of students, but also closely integrate the key competences of the discipline with the characteristics of the discipline itself is a problem that requires us to constantly think, explore and strive to solve in actual education and teaching [1].

As an important monitoring mechanism for teaching activities, classroom teaching evaluation is an important means to promote the development of students and teachers, improve the quality of education and teaching, and achieve the goals of classroom teaching. It not only determines the direction of classroom teaching, but also has a profound impact on the level and height of teaching quality. However, in the traditional classroom teaching evaluation practice in our country, the evaluation of students pays too much attention to academic performance and ignores the formation of students’ qualities, and pays too much attention to the ranking order and ignores the student’s learning process, and pays too much attention to the teacher’s dominant position and ignores the students’ active participation. The classroom teaching evaluation is like a short board, which greatly limits the realization of classroom teaching benefits [2]. Therefore, the research on the ideological and political classroom teaching evaluation based on the key competences of the discipline is not only a continuous and in-depth discussion of the new version of the ideological and political curriculum standards, but also to answer the demands and expectations of the party and the country for education, that is, who to train and how to train people

First of all, the developmental evaluation method and concept have opened up a new research area for teaching evaluation of ideological and political courses, and the developmental evaluation method can make the role of ideological and political education to students’ moral education play a better role, and can enable the country to better provide moral education services to students [3]. Secondly, through the research of this paper, it is found that it can further enrich the relevant theoretical system, improve the teaching evaluation theory, guide the practice with the theory, and make the evaluation method that promotes development more maturely implemented in the evaluation of ideological and political courses. The enrichment of the theoretical system and the maturity of practice can enhance the effectiveness of the teaching evaluation of political lessons and promote the true realization of the goal of moral education. Thirdly, the research in this paper can make the developmental evaluation theory better serve the teaching of politics, help to achieve the teaching goals, improve the quality of teaching, and promote the continuous progress of teachers and students through developmental evaluation.

2 Related works

The literature [4] put forward ‘education evaluation”, and believes that “education evaluation is essentially a process of determining how much education goals are achieved in the curriculum and teaching program’. The literature [5] believed that classroom evaluation is an evaluation of students’ learning achievements, and does not emphasize evaluation of teachers’ teaching quality. The literature [6] believed that classroom evaluation is a process of improving teaching by collecting information from students during the learning process. These two views mainly emphasize the evaluation of students and the formative function of evaluation. The focus of foreign classroom evaluation research is the evaluation of student learning. The Western world has produced a series of learning theories in the process of exploring how humans learn and how learning occurs. From cognitive learning theory to humanistic learning theory and from constructivist theory to situational learning theory, the study of learning theory has been continuing and developing. There is also a clear definition of “learning assessment” for “learning evaluation”, which refers to the evaluation of student learning [7]. At present, the international learning evaluation research community regards the combination of evaluation and teaching as the main trend of research, that is, how to effectively evaluate students in classroom teaching to achieve the purpose of promoting student learning and cultivating student literacy. In recent years, researchers from various countries have studied learning evaluation from different perspectives and put forward new ideas for learning evaluation, including formative evaluation, developmental evaluation, evaluation of learning promotion, evidence-centric evaluation, authenticity evaluation, and student participation evaluation [8]. The classroom evaluation has a formative function. The literature [9] cited formative evaluation to classroom teaching and student learning. The literature [10] proposed to pay more attention to teachers’ feedback to students and students’ self-evaluation and self-monitoring. In the 1990 s, the literature [11] did further research on formative evaluation and proposed to combine formative evaluation with teaching. On this basis, the “evaluation of learning promotion” replacing the formative evaluation was first proposed, and it believed that the origin of the classroom is students, and the origin of classroom evaluation is to promote student learning. The main points of the evaluation concept are students need to participate in the evaluation, teachers need to provide effective feedback on the student’s learning process and effects, and its emphasis on students’ self-evaluation and reflection. The literature [12] proposed authenticity evaluation and emphasized to investigate the learning effect and mastery of students’ knowledge and skills, as well as the development of various complex abilities such as critical thinking, cooperative communication, etc.in real scenarios and real tasks. The authenticity learning evaluation uses the evaluation methods of authenticity tasks and gauges, as well as evaluation tools such as portfolios, concept maps, role-playing and diaries to evaluate students. The literature [13] proposed “evidence-centered evaluation". This method emphasizes that the evaluation should focus on the student’s learning process, clearly describe the process of the student’s knowledge acquisition, learning skills, and comprehensive development, obtain effective evidence that reflects the student’s learning and ability level, and evaluate the student based on the evidence. The literature [14] has established a set of evaluation system that points to student learning through years of reform and proposed evaluation for learning, evaluation as learning, and evaluation of learning to replace the previous diagnostic evaluation, formative evaluation, and final evaluation.

The literature [15] believed that classroom evaluation is a process in which teachers collect and analyze students’ learning information in the classroom, judge students’ learning through certain standards, and then make teaching decisions, the literature [16] believed that classroom evaluation is an evaluation of classroom teaching, and literature [17] believed that classroom evaluation is an evaluation of the “learning” of students, the “teaching” of teachers and the relationship between teaching and learning. The differences between these three views are mainly focused on the evaluation object. Since the reform of the new curriculum, the emphasis has been placed on students’ dominance in classroom teaching. Therefore, the current academic research object on classroom evaluation has begun to shift to evaluation of student learning. The literature [18] believed that classroom evaluation is the activity and process of collecting and analyzing the learning information of students in order to grasp the learning status of students, clarify the teaching effect of the classroom, and promote the efficient development of students. In daily teaching, classroom evaluation includes two types: one is direct feedback from teachers in the classroom teaching process, such as evaluating language, emotions, expressions, and actions; the other type is the evaluation of student learning, including the evaluation of practice questions and assignments, the setting of evaluation tasks in the classroom, the questions and observations of students in the classroom, etc. [19].

The literature [20] put forward from the perspective of evaluation content, learning evaluation is to judge the personality qualities acquired by students in the learning process and the learning process itself. Literature [21] puts forward from the perspective of evaluation process that learning evaluation is the process of collecting the performance and learning effects of students in the learning process through observation, investigation and testing and then making value judgments to revise and reflect on the learning objectives, which is based on learning objectives. Unique representation of intuitionistic fuzzy model and various applications related to it is proposed based on critical decision making [22]. Intuitionistic fuzzy model is utilised for enhancing the fingerprint and it’s matching with feature extraction model [23]. Histogram based cluster selection is used for skin lesion segmentation with help of fuzzy c-means [24]. Rule based information fuzzy system for analyzing for localizing thrombus in artery [25].

3 Determination of evaluation index weight

In this paper, the evaluation index weights will be calculated and determined using expert scoring and analytic hierarchy process. This article will use Yaahp software to calculate the index weight [26].

The first step is to collect the expert’s scoring results; the second step is to input the expert’s scoring results on the importance of the indicators into Yaahp software to calculate and obtain the weight of each indicator; The third step is to adjust the constructed judgment matrix according to the consistency test results obtained by Yaahp software; the fourth step is to form a complete fuzzy hierarchy evaluation index weight system. The specific process is shown in Fig. 1 [27, 28].

Fig. 1

Flow chart for determining the weight of fuzzy hierarchy evaluation indicators.

The steps to determine the index weight are as follows:

(1) Building a hierarchical structure model

According to the evaluation purpose of the problem to be studied in the paper, the evaluation purpose is divided into multiple dimensions, and the evaluation indicators are designed under these dimensions, which can be divided into first-level indicators, second-level indicators, and third-level indicators. The layer below the target layer is the criterion layer U₁, U_ij, and their corresponding relationship is [27]: $U = (U_{1}, U_{2}, U_{3}, Λ, U_{m})$ (1) $U = (U_{i 1}, U_{i 2}, U_{i 3}, Λ, U_{im})$ (2)

Among them, i = 1, 2, 3, ⋯ , m ; j = 1, 2, 3, ⋯ , n.

(2) Constructing a judgment matrix of pairwise comparison

After the hierarchical structure model is established, the membership relationship between the upper and lower levels of each element is determined accordingly as shown in Fig. 2. For example, taking the target layer U and the criterion layer U_i as examples, the following judgment matrices A and A_i can be established respectively: $A = [\begin{matrix} A_{11} & A_{12} & Λ & A_{1 m} \\ A_{21} & A_{22} & Λ & A_{2 m} \\ M & M & O & M \\ A_{m 1} & A_{m 2} & Λ & A_{mm} \end{matrix}]$ (3) $A = [\begin{matrix} a_{11} & a_{12} & Λ & a_{1 m} \\ a_{21} & a_{22} & Λ & a_{2 m} \\ M & M & O & M \\ a_{n 1} & a_{n 2} & Λ & a_{nm} \end{matrix}]$ (4)

Among them, A_ij (i = 1, 2, 3, ⋯ , m ; j = 1, 2, 3, ⋯, m) and a_ij (i = 1, 2, 3, ⋯ , n ; j = 1, 2, 3, ⋯ , n) often take the following values:

The software Yaahp is used to calculate the expert scores to get the weight of each indicator (taking the first-level indicator as an example as in Table 1).

(3) Consistency test

Since the matrix is scored by experts, there is a certain degree of subjectivity. Through the consistency test, the inconsistency of the matrix can be controlled within the allowable range as in Fig. 3. The specific step is as follows:

First, the maximum feature root of the matrix A-B is calculated: $λ_{max} = \sum_{i = 1}^{n} \frac{A_{ω i}}{n_{ω i}}$ (5)

Second, the consistency index (CI) is calculated: $CI = \frac{λ_{max} - n}{n - 1}$ (6)

Again, corresponding to the average random consistency index RI (Random Index), calculate CR (Consistency Ratio) $CR = \frac{CI}{RI}$ (7)

When CI < 0.1, CR < 0.1, the judgment matrix passes the consistency test, otherwise the consistency of the judgment matrix fails. At this time, the algorithm needs to return to modify the judgment matrix until the consistency test is passed as in Table 2. Through the Yaaph software, the consistency test results of the 6 judgment matrices are calculated. The results are shown in Table 3. It can be seen that the consistency ratio of all judgment matrices is less than 0.1, so all judgment matrices pass the consistency test.

Table 1

T.L.Saaty ‘s 1–9 scale method

Scale	The meaning of scale
1	The former is as important as the latter
3	The former is slightly more important than the latter
5	The former is obviously more important than the latter
7	The former isstrongly more important than the latter
9	The former is extremely more important than the latter
2,4,6,8	represents the median value of the above adjacent judgment
Reciprocal	If the ratio of the importance of index i and element j is a, then the ratio of the importance of element j and element i is 1/a

Table 2

Average consistency index

Stage	RI	Stage	RI
1	0.0000	6	1.2412
2	0.0000	7	1.3221
3	0.5864	8	1.412
4	0.9024	9	1.4621
5	1.1225	10	1.4902

Table 3

The output table of the consistency test results of the judgment matrix

	CR	W1	λmax	Matrix notes
Matrix 1	0.0187	1	5.0836	Teaching Evaluation
Matrix 2	0.0037	0.0479	3.0038	Teaching preparation
Matrix 3	0.0338	0.1072	6.2121	Teaching implementation
Matrix 4	0.0408	0.1072	4.1088	Knowledge acquisition
Matrix 5	0.0040	0.2695	4.0105	Behavior improvement
Matrix 6	0.0373	0.4687	3.0388	Performance improvement

4 Comprehensive evaluation based on fuzzy comprehensive evaluation method

The fuzzy set theory was first proposed by American automatic control expert L.A. Lad in 1965. Moreover, he founded fuzzy mathematics on this basis. Fuzzy mathematics can be applied to study the relationship between fuzzy things and can be quantitatively analyzed using mathematical methods. The fuzzy comprehensive evaluation method is based on fuzzy mathematics and uses fuzzy sets as a theoretical basis to comprehensively evaluate a fuzzy thing from various elements.

This article uses the fuzzy comprehensive evaluation method to calculate the comprehensive score of the index system as in Table 4. The main steps of this evaluation method are:

(1) Establishing evaluation index set

The index set u of fuzzy comprehensive evaluation objects is established to form a set of all indexes of evaluation objects, and u can be expressed as: $U = (U_{1}, U_{2}, U_{3}, Λ, U_{j})$ (8)

Among them, the element U_j represents the ith factor affecting the evaluation object. For objects with multiple evaluation factors, there is also a secondary index U₁, which can be expressed as: $U_{1} = (U_{i 1}, U_{i 2}, U_{i 3}, Λ, U_{ij})$ (9)

Among them, U_ij represents the J-th factor index of the i-th criterion layer, and i = 1, 2, 3, ⋯ , m ; j = 1, 2, 3, ⋯ , n.

(2) Defining comment set V and score F

V can generally be expressed as: $V = (V_{1}, V_{2}, V_{3}, Λ, V_{μ})$ (10)

This article divides the evaluation of each index into five levels: very consistent, consistent, general consistent, inconsistent, and very inconsistent. Therefore, the comment set is expressed as:

V = (V₁, V₂, V₃, ⋯ , V_u) = (very consistent, consistent, general, inconsistent, and very inconsistent)

The score set corresponding to the comment set is F = (F₁, F₂, F₃, F₄, F₅), and F represents five scores corresponding to the comment set.

(3) Establishing an evaluation matrix R_n to determine the membership of each evaluation factor

According to the created comment set V, the degree of membership of each index factor U₁ and U_ij in the set U is calculated. Through calculation, the fuzzy matrix R of the fuzzy relationship between U and V, the fuzzy matrix R₁ of the fuzzy relationship between U₁ and V, and the fuzzy matrix R_ij of the fuzzy relationship between U_ij and V can be obtained. $R = (\begin{matrix} U_{1} | V \\ U_{2} | V \\ M \\ U_{m} | V \end{matrix}) = [\begin{matrix} r_{11} & r_{12} & Λ & r_{1 p} \\ r_{21} & r_{22} & Λ & r_{2 p} \\ M & M & O & M \\ r_{m 1} & r_{m 2} & Λ & r_{mp} \end{matrix}]$ (11)

Among them, the element r_ij (i = 1, 2, 3, ⋯ , m ; j = 1, 2, 3, ⋯ , p) in the fuzzy matrix R represents the membership degree of each element U₁ in the set U to each rating level in the comment set V.

Similarly, the following results can be obtained: $R = (\begin{matrix} U_{i 1} | V \\ U_{i 2} | V \\ M \\ U_{in} | V \end{matrix}) = [\begin{matrix} r_{i 11} & r_{i 12} & Λ & r_{i 1 p} \\ r_{i 21} & r_{i 22} & Λ & r_{i 2 p} \\ M & M & O & M \\ r_{in 1} & r_{in 2} & Λ & r_{inp} \end{matrix}]$ (12)

Among them, the element r_ijk (j = 1, 2, 3, ⋯ , n ; k = 1, 2, 3, ⋯ , p) in R₁ represents the membership degree of each element U_ij in the set U₁ to each level in the comment set V.

(4) Computing fuzzy comprehensive evaluation set

According to the index weight ω_n and the evaluation matrix R_n, the fuzzy comprehensive evaluation set Y_n of the index system is calculated. $Y_{n} = ω_{n} * R_{n} = (y_{n 1}, y_{n 2}, y_{n 3}, Λ, y_{nk})$ (13)

(5) Calculating fuzzy comprehensive score X

According to the calculated fuzzy comprehensive evaluation set and the set score set F, the final fuzzy comprehensive score value is obtained. $X = Y_{n} \times F = (y_{n 1}, y_{n 2}, y_{n 3}, Λ, y_{nk}) \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix})$ (14)

Based on the model level, index structure, and survey results and scoring criteria of the questionnaire survey, the fuzzy evaluation frequency distribution of this study is obtained:

The evaluation of each index in this article is divided into five levels: very consistent, consistent, general consistent, inconsistent, and very inconsistent, corresponding to 100 points, 80 points, 60 points, 40 (1) Comprehensive evaluation value of index layer as mentioned in Table 5.

For example, set goals. (C₁). In the questionnaire survey, according to the selection of C₁ in 384 valid questionnaires, 19% of people think it is very consistent, 21% of people think it is in consistent, 49% of people think it is in general consistent, and 8% of people think it is inconsistent. 3% of people think it is very inconsistent. Therefore, after normalizing the matrix (0.19, 0.21, 0.49, 0.08, 0.03), the fuzzy comprehensive evaluation value obtained is: $X_{1} = (0.19 0.21 0.49 0.08 0.03) \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 69$ (15)

Similarly, the fuzzy comprehensive evaluation score of the 20 indicators of index layer is shown in Table 6, and the statistical graph is drawn as shown in Fig. 4.

Table 4

Score sets corresponding to scale comments

Index	Fully compliant	Basically	Normal	Not quite in line	Not at all
	(F1)	(F2)	(F3)	(F4)	(F5)
Score	100	80	60	40	20

Table 5

Score table of fuzzy comprehensive evaluation of index layer

Indicator layer	Fuzzy evaluation value
Training goal promotion	70.38
Training needs analysis	43.45
Training notice	93.02
training content	70.58
Training materials	76.70
Teaching method	75.48
Teaching faculty	78.74
Training facility	71.40
Training management	90.37
Political theory	94.45
legal knowledge	91.80
working ability	65.28
Scientific and cultural knowledge	80.17
Political discrimination	94.86
Administrative capacity according to law	80.58
Public service capacity	76.50
Innovation capacity	55.08
Personal performance	72.42
Organizational Performance	71.40
Public satisfaction	55.49

Table 6

Fuzzy comprehensive evaluation scores of criterion layer

Criterion layer	Fuzzy evaluation value
Training preparation	59.211
Training implementation	70.6554
Knowledge acquisition	85.272
Behavior improvement	82.8648
Performance improvement	69.3294

Fig. 2

Hierarchical structure diagram of fuzzy hierarchical evaluation.

Fig. 3

Evaluation index weights.

Fig. 4

Score diagram of fuzzy comprehensive evaluation of index layer.

(2) Calculation of comprehensive evaluation value of criterion layer

According to the evaluation table of the survey data provided as in Fig. 5, the fuzzy evaluation matrix is as follows: The fuzzy evaluation matrix of training preparation is: $R_{1} = (\begin{matrix} 0.19 & 0.21 & 0.49 & 0.08 & 0.03 \\ 0 & 0 & 0.22 & 0.69 & 0.09 \\ 0.43 & 0.33 & 0.21 & 0.03 & 0 \end{matrix})$ (16)

The fuzzy evaluation matrix of training implementation is: $R_{2} = (\begin{matrix} 0.11 & 0.3 & 0.53 & 0.06 & 0 \\ 0.18 & 0.4 & 0.42 & 0 & 0 \\ 0.16 & 0.38 & 0.42 & 0.04 & 0 \\ 0.29 & 0.28 & 0.43 & 0 & 0 \\ 0.05 & 0.4 & 0.55 & 0 & 0 \\ 0.56 & 0.31 & 0.13 & 0 & 0 \end{matrix})$ (17)

The fuzzy evaluation matrix of knowledge acquisition is: $R_{3} = (\begin{matrix} 0.74 & 0.15 & 0.11 & 0 & 0 \\ 0.6 & 0.3 & 0.1 & 0 & 0 \\ 0.23 & 0.09 & 0.33 & 0.35 & 0 \\ 0.3 & 0.33 & 0.37 & 0 & 0 \end{matrix})$ (18)

The fuzzy evaluation matrix of behavior improvement is: $R_{4} = (\begin{matrix} 0.72 & 0.21 & 0.07 & 0 & 0 \\ 0.3 & 0.36 & 0.33 & 0.01 & 0 \\ 0.2 & 0.35 & 0.45 & 0 & 0 \\ 0.08 & 0.08 & 0.34 & 0.46 & 0.04 \end{matrix})$ (19)

The fuzzy evaluation matrix of performance improvement is: $R_{5} = (\begin{matrix} 0.19 & 0.28 & 0.42 & 0.11 & 0 \\ 0.15 & 0.26 & 0.53 & 0.06 & 0 \\ 0.1 & 0.14 & 0.21 & 0.19 & 0.05 \end{matrix})$ (20)

According to the weight distribution, the weights of the first-level indicators and the second-level indicators are as follows: $\begin{matrix} A = (0.0478 0.1071 0.1071 0.2694 0.4686) \\ A_{1} = (0.1096 0.5813 0.3092) \\ A_{2} = (0.2445 0.619 0.2445 0.1023 0.1023) \\ A_{3} = (0.4609 0.0726 0.1560 0.3104) \\ A_{4} = (0.4547 0.2630 0.1411 0.1411) \\ A_{5} = (0.2305 0.6333 0.1062) \end{matrix}$ (21)

According to the formula, the comprehensive evaluation set of the index system can be expressed as Y_n (n = 1, 2, 3, 4, 5), then the fuzzy comprehensive evaluation value of training preparation. $\begin{matrix} Y_{1} = A_{1} \times R_{1} = (0.1096 0.5813 0.3092) \times \\ (\begin{matrix} 0.19 & 0.21 & 0.49 & 0.08 & 0.03 \\ 0 & 0 & 0.22 & 0.69 & 0.09 \\ 0.43 & 0.33 & 0.21 & 0.03 & 0 \end{matrix}) \\ = (0.1538 0.1251 0.2465 0.4191 0.0556) \end{matrix}$ (22)

Similarly, the following results can be obtained: $\begin{matrix} Y_{2} = A_{2} \times R_{2} = (0.2105 0.3320 0.4330 0.0245 0) \\ Y_{3} = A_{3} \times R_{3} = (0.5136 0.2074 0.2243 0.0547 0) \\ Y_{4} = A_{4} \times R_{4} = (0.4458 0.2508 0.2301 0.0675 0.0058) \\ Y_{5} = A_{5} \times R_{5} = (0.1511 0.2525 0.4673 0.086 0.0391) \end{matrix}$ (23) $\begin{matrix} X_{11} = (0.1538 0.1251 0.2465 0.4191 0.0556) \\ \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 58.25 \end{matrix}$ (24)

The fuzzy comprehensive evaluation value of training implementation is: $\begin{matrix} X_{21} = (0.2105 0.3320 0.4330 0.0245 0) \\ \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 69.27 \end{matrix}$ (25)

The fuzzy comprehensive evaluation value of knowledge acquisition is: $\begin{matrix} X_{31} = (0.5136 0.2074 0.2243 0.0547 0) \\ \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 83.60 \end{matrix}$ (26)

The fuzzy comprehensive evaluation value of behavior improvement is: $\begin{matrix} X_{41} = (0.4458 0.2508 0.2301 0.0675 0.0058) \\ \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 81.24 \end{matrix}$ (27)

The fuzzy comprehensive evaluation value of performance improvement is: $\begin{matrix} X_{51} = (0.1551 0.2525 0.4673 0.086 0.0391) \\ \times (\begin{matrix} 100 \\ 80 \\ 60 \\ 40 \\ 20 \end{matrix}) = 67.97 \end{matrix}$ (28)

Through calculation, it can be concluded that the fuzzy comprehensive evaluation value score of the criterion layer is:

5 Intelligent evaluation model of ideological and political education quality

Our country promotes quality education, and quality education needs to be directed to all students. For the development of each student, the new student-oriented curriculum reform concept should be implemented into the classroom. In the classroom, teachers should pay attention to the development needs of each student, give them equal attention and incentives, create equal opportunities and conditions for learning progress, help correct positive or bad thoughts or behaviors, so that students can develop in a more perfect direction.

Figure 6 shows the artificial intelligence evaluation model of ideological and political education. The model is a three-layer network structure, where the user layer is mainly school staff and ideological and political teachers. However, in the actual ideological and political classroom, teachers still cannot convert the evaluation of students’ core quality. At present, teachers still regard the basic knowledge of the subject and the skills of major topics as the focus of ideological and political studies, thus ignoring the cultivation of students’ key abilities and essential qualities.100 people are surveyed, and the results are shown in Fig. 7.

Fig. 5

Statistical diagram of fuzzy comprehensive evaluation scores at the criterion level.

Fig. 6

The artificial intelligence evaluation model of ideological and political education.

Fig. 7

The way students learn in high school ideological and political classes.

In a survey of students about the question “How do you usually study in the political class?”, it was found that the current high school students’ learning methods in the political classroom are mainly listening and copying notes, accounting for 57%, while the learning methods of active thinking, group discussion and personal activities account for the minority. This also reflects that the teaching methods of the ideological and political classroom have not been reformed quickly under the requirements of core quality, and it also shows that teachers pay more attention to students’ subject knowledge learning in learning evaluation. Therefore, in the question “What aspects of the ideological and political class teachers pay more attention to you?”, 67% of the students answered ‘the ability to use political subject knowledge to solve problems’, 22% of the students answered ‘reciting the concept of knowledge’ and only 11% of the students answered that teachers pay attention to the evaluation of their “core quality development level’. This directly reflects that the current ideological and political teachers pay little attention to the students’ core quality level in the evaluation. Even in the question “Do you understand core quality?", only one-third of the students understand core quality. This shows that the current implementation of core quality in classroom teaching and evaluation is far from enough. The statistical results are shown in Fig. 8.

Fig. 8

Evaluation contents of political teachers for students.

In the interviews and classroom observations with teachers, we found that even under the influence of the current core quality background, some teachers still regard classroom learning evaluation as a means of testing students’ knowledge and judging their academic performance and progress in daily teaching. Moreover, teachers regard classroom learning evaluation as a vassal of external examinations, and still adopt a series of paper-and-pencil tests such as traditional knowledge point recitation, silent writing, and test paper test to evaluate students’ performance and ability, but do not pay much attention to the evaluation of students’ comprehensive quality and ability development in the learning process. In addition, it is difficult to measure the true appearance of students’ emotions, thoughts, and qualities only by using paper and pencil tests. At the same time, it is difficult to fully grasp the development of students’ comprehensive qualities by grading students’ performance, writing some suggestions or encouraging words, and more difficult to complete the current core quality requirements. In the survey, we also found that although the traditional evaluation method of paper-and-pencil test still occupies the dominant position in classroom teaching, some emerging evaluation methods also appear in the classroom. Among the evaluation methods, the more common methods mainly include daily learning behavior evaluation and verbal timely evaluation. Some teachers use rating scales to evaluate students’ individual and group behaviors and use growth record bags to record students’ learning process and results. These evaluation methods can play an effective role in evaluating students’ core quality development. However, the popularization of these methods and the proposal of more effective evaluation methods also require continuous innovation and development to further effectively implement the core quality of students. The learning evaluation method carried out by teachers is shown in Fig. 9.

Fig. 9

Evaluation methods of learning carried out by teachers.

Fig. 10

The process of learning evaluation implementation in the ideological and political classroom.

The connotation of expressive evaluation makes many people find it unpredictable. They think that its forms are diverse, and think that it is the main feature of students to show behavior and evaluate students’ works and performance through activities. In fact, the key point that distinguishes performance evaluation from general evaluation is that its evaluation content is not general knowledge literacy, but the higher order thinking and complex cognitive ability that students show in the process of analyzing and solving problems in actual situations. This is consistent with the core quality currently advocated, so performance evaluation is an important means of implementing core quality. The implementation process of ideological and political classroom learning evaluation under the perspective of core quality is roughly divided into the following four steps:

Under the instruction of the new curriculum standards, especially under the perspective of core quality, we must take evaluation as a way to cultivate students’ developmental abilities, and truly integrate evaluation and teaching to achieve consistency in teaching, learning and evaluation. At this time, the classroom as a key stage for cultivating students will inevitably provoke the burden of implementing core quality. The classroom evaluation should reposition its role under the new background of core quality. It is no longer a student selection officer and teacher rater, but a supporter of student and teacher growth. In the process of assisting, we should pay attention to the key role of performance evaluation in core quality evaluation. Performance evaluation focuses on the student’s learning process, and takes the students’ complex abilities and higher-order thinking in the process of solving real situation problems as evaluation content, which is in line with the cultivation goals of the core quality in the new curriculum standard and coincides with the concept of the active subject curriculum. In this field, we have to go a long way. With the advent of the information age, the acceleration of the globalization process and the rapid development of science and technology have placed higher and higher requirements on everyone’s own development. In the face of increasingly complicated real life, the fixed and routine subject knowledge that the individual emphasized by traditional education can no longer meet the needs of social development. The progress of the times has called for education and requires individuals to have meticulous and high-level thinking and judgment, understand teamwork, and the ability to create and regenerate, thereby further solving challenging and complex tasks in the real world. This kind of education requires that the current teaching methods and evaluation methods can surpass themselves and complete the reform. All in all, the model constructed in this study meets actual needs and has certain practical significance.

6 Conclusion

How to achieve the actual effect of teaching is the focus of attention in the field of education and the practical requirements of the current teaching situation as in Fig. 10. The ideological and political course in colleges and universities is a major feature of the development of my country’s higher education and an important practical path to implement the fundamental task of establishing morality. The effectiveness of college ideological and political teaching directly determines the quality of college personnel training. Based on the fuzzy analytic hierarchy process model, this study builds an artificial intelligence evaluation model for ideological and political education based on machine learning. The model constructed in this study is a three-layer network structure, in which the user layer is mainly school staff and ideological and political teachers. These personnel are connected to the system through a human-computer interaction interface. After the user enters the data, he will enter the data exchange center and the data processing center, combine the expert system to evaluate the teaching process, and feedback the data to the user terminal through the system data transmission network. In addition, this study uses simulation experiments to analyze model performance. From the point of view of running effect and running speed, this research model meets the actual needs of the system, so it can be applied to the evaluation process of ideological and political teaching quality in colleges and universities.

References

Al-Maamari

, Response Rate and Teaching Effectiveness in Institutional Student Evaluation of Teaching: A Multiple Linear Regression Study[J], Higher Education Studies 5(6) (2015), 9.

Angell

and Tewell

, Teaching and Un-Teaching Source Evaluation: Questioning Authority in Information Literacy Instruction[J], Communications in Information Literacy 11(1) (2017), 95–121.

Wang

, Wang

and Hu

, College English Classroom Teaching Evaluation Based on Particle Swarm Optimization –Extreme Learning Machine Model[J], International Journal of Emerging Technologies in Learning 12(5) (2017), 82.

Brkovic

and Chiles

, ‘Spector - the sustainability inspector’: Participatory teaching, learning and evaluation game for architects, architecture students and pupils[J], Facta Universitatis 14(1) (2016), 1–20.

Devi

S.S.

, Singh

N.H.

and Laskar

R.H.

, Fuzzy C-Means Clustering with Histogram based Cluster Selection for Skin Lesion Segmentation using Non-Dermoscopic Images [J], International Journal of Interactive Multimedia and Artificial Intelligence. (2020), 6 (Special Issue on Soft Computing) 26–31.

Eckler

, Greisberger

, Höhne

, et al., Blended learning versus traditional teaching-learning-setting: Evaluation of cognitive and affective learning outcomes for the inter-professional field of occupational medicine and prevention / Blended Learning versus traditionelles Lehr-Lernsetting: Evaluierung von kognitiven und affektiven Lernergebnissenfür das interprofessionelle Arbeitsfeld Arbeitsmedizin und Prävention[J], Nephron Clinical Practice 4(2) (2017), 109–121.

Lalvarmawi

, Banik

and Anita Devi

, Feedback of medical students on teaching and evaluation methodology in Physiology[J], National Journal of Physiology Pharmacy & PharMacology 5(2) (2015), 1.

Garofalo

, Mota-Moya

, Munday

, et al., Total Extraperitoneal Hernia Repair: Residency Teaching Program and Outcome Evaluation[J], World Journal of Surgery 41(1) (2017), 1–6.

Gong

and Liu

, Consideration of Evaluation of Teaching at Colleges[J], Open Journal of Social Sciences 04(7) (2016), 82–84.

10.

Heitkamp

S.J.

, Rüttermann

and Gerhardt-Szép

, Work shadowing in dental teaching practices: evaluation results of a collaborative study between university and general dental practices[J], Bmc Medical Education 18(1) (2018), 99.

11.

Jiang

and Wang

, Evaluation of Teaching Quality of Public Physical Education in Colleges Based on the Fuzzy Evaluation Theory[J], Journal of Computational and Theoretical Nanoence 13(12) (2016), 9848–9851.

12.

, Li

and Ge

, Application of Data Mining in the Colleges’ in-Class Teaching Quality Evaluation System[J], Journal of Computers 10(3) (2015), 166–175.

13.

Linhares

R.N.

, Alcântara

C.M.G.

, Gonçalves

E.Á.

, et al., Teaching Evaluation by Teachers from Brazil and Portugal: A Comparative Analysis[J], American Journal of Educational Research 5(5) (2017), 546–551.

14.

Liu

and Chen

, Research on Fuzzy Comprehensive Evaluation in Practice Teaching Assessment of Computer Majors[J], International Journal of Modern Education & Computer Science 7(11) (2015), 12–19.

15.

Manickam

and Devarasan

, Level 2 feature extraction for latent fingerprint enhancement and matching using type-2 intuitionistic fuzzy set [J], International Journal of Bioinformatics Research and Applications 15(1) (2019), 33–50.

16.

Cerón

M.S.

and Cruz

F.M.S.C.

, The Evaluation of Teaching: Some Consequences for Latin America[J], Revista Mexicana De Investigacion Educativa 20(67) (2015), 1233–1253.

17.

Oliveros

M.A.

, García

and Valdez

, Evaluation of a Teaching Sequence Regarding Science, Technology and Society Values in Higher Education[J], Creative Education 6(16) (2015), 1768–1775.

18.

Murcia

J.A.M.

, Torregrosa

Y.S.

and Belando

, Questionnaire evaluating teaching competencies in the university environment, Evaluation of teaching competencies in the university[J], Naer Journal of New Approaches in Educational Research 4(1) (2015), 54–61.

19.

Tran

N.D.

, Reconceptualisation of approaches to teaching evaluation in higher education[J], Issues in Educational Research 25(1) (2015), 50–61.

20.

Huang

, Analysis and Design of University Teaching Evaluation System Based on JSP Platform[J], International Journal of Education & Management Engineering 7(3) (2017), 43–50.

21.

Porozovs

, Liepniece

and Voita

, Evaluation of the Teaching Methods Used in Secondary School Biology Lessons[J], Nephron Clinical Practice 7(1) (2015), 60–66.

22.

Reisenwitz

T.H.

, Student Evaluation of Teaching: An Investigation of Nonresponse Bias in an Online Context.[J], Journal of Marketing Education 38(4) (2015), 139–144.

23.

Ngan

R.T.

, Ali

, Fujita

, Giang

N.L.

, Manogaran

and Priyan

M.K.

, A New Representation of Intuitionistic Fuzzy Systems and Their Applications in Critical Decision Making [J], IEEE Intelligent Systems.

24.

Roopa

C.K.

and Harish

B.S.

, Automated ECG Analysis for Localizing Thrombus in Culprit Artery Using Rule Based Information Fuzzy Network [J], International Journal of Interactive Multimedia and Artificial Intelligence (2020), 16–25.

25.

Royal

, A Guide for Making Valid Interpretations of Student Evaluation of Teaching (SET) Results[J], Journal of Veterinary Medical Education 44(2) (2016), 1–7.

26.

Müller

, Montano

, Poinstingl

, et al., Evaluation of large-group lectures in medicine –development of the SETMED-L (Student Evaluation of Teaching in MEDical Lectures) questionnaire[J], Bmc Medical Education 17(1) (2017), 137.

27.

Zhao

, College Physics Teaching Model Design and Evaluation Research of Students’ Seriousness[J], Open Cybernetics & Systemics Journal 9(1) (2015), 2017–2020.

28.

Zhou

, Li

and Sun

, Teaching performance evaluation by means of a hierarchical multifactorial evaluation model based on type-2 fuzzy sets[J], Applied Intelligence 46(1) (2016), 1–11.