Artificial intelligence based on effectiveness of inverted classroom teaching of college sports

Abstract

This study takes the effectiveness analysis of inverted classroom teaching in colleges and universities as a breakthrough point, and combines artificial intelligence technology with the analysis method of inverted classroom teaching in colleges and universities to enrich the existing methods for analyzing, the behavior of inverted classroom teaching in colleges and universities to realize the effectiveness of inverted classroom teaching in colleges and universities analysis. This research first constructs an analytical framework for the teaching behaviors of college physical education inverted classrooms based on artificial intelligence technology, which consists of observation dimension and the evaluation dimension. In order to further test the scientifically and operability of the analytical framework, taking emotion recognition as an example, practical operations are combined with specific examples to obtain visual analysis results. This study expands the dimension and depth of analysis of the behavior of inverted sport in classroom teaching in sport inversion colleges and universities, and has obvious advantages in saving manpower and real-time visual display. Through the analysis of the effectiveness of physical education inverted classroom teaching in sports inversion colleges and universities through artificial intelligence technology, the use of technology to participate in the analysis of physical education inverted classroom teaching behaviors in sports inverted colleges and universities, shorten the evaluation time, expand the evaluation dimension, improve the evaluation efficiency, achieve real-time feedback, real-time attention to classroom effects. Effectively regulating the inverted classroom teaching behavior of college physical education can promote the cultivation of teachers’ professional abilities, scientifically and accurately improve and correct teaching problems, and improve the quality of education and teaching. Eventually, students will achieve comprehensive self-evaluation of students, and promote personalized and standardized growth of students.

Keywords

Artificial intelligence inverted classroom teaching effectiveness physical education analysis

1 Introduction

If physical education teachers want to be a major, they must have certain norms and guidelines. At present, the core of physical education teacher specialization in the implementation of physical education curriculum standards is the specialization of physical education [1]. The specialization of physical education teachers in colleges and universities is the specialization of physical education, and the specialization of physical education is reflected in many aspects such as teaching methods, teaching organization and reasonable allocation of teaching time [2]. We can also understand teacher teaching specialization as teachers’ comprehensive teaching literacy. The improvement of comprehensive teaching literacy requires teachers to start with improving their basic teaching skills, such as writing lesson plans, writing summaries, and writing papers. Only when the teacher’s comprehensive teaching literacy is improved will teach become more professional. The specialization of physical education teachers in colleges and universities is an internal requirement for the development and reform of physical education in universities and colleges [3]. It is also a requirement of the current integration and penetration of scientific knowledge, and it is also a requirement for education to adapt to the development of the 21st century. The establishment of the theory of lifelong learning by physical education teachers is an inevitable trend of educational development and reform.

At present, the relatively new and popular direction in the field of artificial intelligence research is machine learning. Behind human learning behavior is a complex brain science processing mechanism, which is machine learning theory [4]. It is mainly based on computer simulation and the process of acquiring knowledge by humans. It uses a large amount of data and various algorithms to train a model that can solve specific problems. This model has a certain generalization ability. When entering new data, Effective results can be obtained, and the ultimate goal is to acquire knowledge from the data [5]. Hung C Y and others published a paper on the subject of teaching effectiveness. By reviewing 12 of them, an analysis of the inverted classroom teaching of physical education in colleges was carried out from the perspective of key factor analysis, cultural influence, participants, and teacher guide [6]. From the widespread dissemination of popular large-scale modern educational technology, Yoon S Y found that the flipped classroom, E-Learning and other teachers lacked effective feedback mechanisms, resulting in low teaching efficiency. Therefore, he proposed a slightly adaptive teaching method and Tools to assist these technologies to promote the development of education and teaching [7]. Kim H used data mining techniques such as mathematical models and tools to predict effective curriculum transmission strategies, used for regression analysis and fit testing of student behavior, used emerging technologies to diagnose and predict college physical education inverted classroom teaching behavior, combined with student classroom performance, teachers adjust reasonable teaching activities to improve the effect of college physical education inverted classroom teaching, and lay the foundation for the improvement of college physical education inverted classroom teaching quality [8].

Most of the domestic research focuses on the modification of the classical university inverted classroom teaching analysis system. Guo B and others combined with the current situation of inverted classroom teaching in domestic education informatization colleges and universities, modified FIAS by analyzing the deficiencies of Flanders Interactive Analysis System (FIAS), and proposed an interactive analysis coding system (ITIA) based on information technology [9 –11]. On the basis of improving FIAS and ITIAS, scholar Wang S Y and others proposed an improved Flanders Interactive Analysis System (iFIAS) to effectively observe and evaluate primary and secondary school course [12]. Limniou M and others proposed the 3C-FIAS interactive analysis system, which uses this analysis system to differentiate the analysis of expert teachers and novice teachers in inverted classroom teaching behaviors in colleges and universities. In addition, some scholars have conducted research on the specific application of Flanders interactive analysis method and S-T classroom analysis method in the analysis of inverted classroom teaching in colleges and universities [13]. Cao L and others constructed the PAC Class model for the information interaction between teachers and students, and used this model to formally collect and describe the learning process data and to mine and analyze based on the business domain [14]. Xing Beibei used data collection technologies such as Internet of Things (IOT) perception to acquire large amounts of data generated in inverted classroom teaching in colleges and universities, providing a big data foundation for data mining and learning analysis. Deep learning in the field of artificial intelligence pays more attention to the application of education informatization and is better assisted in teaching under the drive of technology and data [15].

At present, the school is still the main position for physical education. Implementation of the education informatization strategy is also based on the school and is centred on physical education. Therefore, although this article cannot ignore the investigation of this cross-penetration phenomenon, the main focus of the study is school physical education, that is, in all types of schools at all levels, using physical exercises as the basic means to cultivate students’ comprehensive development of the educational process and social activity. In this study, artificial intelligence technology is used to study the inverted classroom teaching behavior of college physical education, and the behaviors of teachers and students and other behaviors in inverted classroom teaching of college physical education are taken as research objects to quantitatively analyze the inverted classroom teaching behavior of college physical education [16]. And through the literature review, comparing several typical college sports inversion classroom teaching behavior analysis systems and methods, combined with the requirements of high-efficiency classrooms to construct the analysis framework of college sports inversion classroom teaching behavior based on artificial intelligence technology, improve college sports inversion classroom teaching Behavior analysis methods. It is conducive to the continuous improvement of the analysis method of the university sport inverted classroom teaching behavior under the background of information technology, and the application efficiency of the university sport inverted classroom teaching analysis. The formation of scientific and effective analysis methods and evaluation systems through in-depth promote college sport Inverted classroom teaching analysis theoretical research expansion and extension.

2 Construction of artificial intelligence model for inverted classroom teaching in college sports

2.1 Construction principles

Teaching goals refer to the clear expression of what kind of changes in students have and achieve certain learning results through the influence of teaching activities. Teaching objectives play an important guiding role in the entire teaching process. Teaching objectives can guide teaching activities, and teaching activities should always be carried out around the realization of teaching objectives. Inverted college sport inverted classroom teaching goals should be consistent with the training objectives, according to the actual needs of students, effective teaching, to achieve the optimization of college sport inverted classroom teaching. Inverted sport teaching mode should cultivate students’ ability to learn and be accustomed to using network resources for learning. Promote students to carry out creative learning, cultivate innovative ability, give students specific questions, let students access information, and finally combine their own knowledge structure to complete tasks and achieve the purpose of innovation. Develop good physical exercise habits and master one or two scientific exercise methods. Eventually, the goal of enlightening students’ minds and promoting students’ upside-down growth will be achieved. Figure 1 show the model of inverted classroom teaching design for college physical education.

Fig. 1

The Design and Process of Inverted Teaching Mode of College Physical Education.

The hardware equipment of the inverted classroom has an innovative scientific layout, advanced IOT technology, IOT architecture, network control method, touch control terminal based on Android architecture, convenient network interconnection technology, teacher computer and student terminal interconnection, instant interaction. The teaching method also has a flexible multi-screen interactive mechanism, and a video display switching mechanism that can flexibly realize a variety of device display switching, a variety of teaching methods and teaching methods. Inverted classrooms are used for real-time interaction in the inverted classroom teaching of college sport. Learners actively construct chemistry learning content in the process of independent and cooperative exploration, from chemistry thoughts, improve subject learning ability, and develop core literacy in chemistry subjects [17, 18]. Technology provides support for teaching, provides a good platform for learners, improves the teaching effect, realizes the viewing and pertinence of teachers’ information and resources, and students’ learning status, and provides corresponding learning suggestions for each student. The teacher’s console uses an advanced network system control architecture, which can realize remote control of various devices, timely control of unexpected situations in the classroom, and targeted adjustment of teaching.

Teaching errors determine the inevitable nature of teaching. However, “error” has two sides. The attitude and method adopted by teachers indirectly affects the students’ learning effect and enthusiasm. In the classroom of inverted teaching of physical education in colleges and universities, if students make mistakes or irregular movements, teachers actively point out and correct mistakes, and turn this “error” into a key problem that students should pay attention to when learning. The emergence of teaching errors leads to what happens under the presupposed premise. Human thinking is jumping and flexible, and it is impossible to complete the teaching tasks without errors according to the established procedures. This also makes the creativity of teacher teaching in the process of inverting teaching in colleges and universities and changeable behavior of students create a generative resource. When students are studying physical education courses, we are not encouraging him to make mistakes, but to turn “errors” into treasures, and carefully convert the “errors” in teaching into teaching activities with the meaning of resource value, which is in line with “reciprocal mutualism”.

2.2 Evaluation characteristics

From the perspective of the evaluation subject, inverted teaching evaluation includes teacher evaluation and student evaluation. It is an intuitive expression of the inverted classroom teaching of physical education under the guidance of teaching objectives. Including the process by which teachers make value judgments on the teaching situation, students’ learning attitudes, behavior habits, and others. By analyzing the relevant data and information generated in the teaching process, and the student’s evaluation process of teachers’ teaching and their own learning status. From the perspective of evaluation content, the inverted teaching evaluation includes two parts of content: online intuitive data evaluation, the learning traces (learning behavior, learning preferences, learning habits) left on the online teaching platform by students in the process of online learning. These data can be said to be the information assets of each student and an important basis for online learning evaluation; offline entity evaluation refers to the learning behavior of students in physical classrooms and teacher teaching, and others [19]. It includes an evaluation of a series of learning activities such as teacher lectures. Group communication and cooperation to solve problems, problem exploration, and movement skills displays. The evaluation target classification comparison is shown in Table 1.

Table 1
Comparison target classification table

Teaching type Target level Simple interpretation of connotation

Traditional teaching Memory Extract relevant information from long-term memory

Understanding Construct knowledge meaning from teaching information

Artificial intelligence assisted teaching Application Apply knowledge and skills learned in new situations

Analysis Decompose materials into elements, clarify the relationship between each element and the relationship with the whole

Evaluation Make value judgments on the learned knowledge and skills according to certain standards

Create Integrate all elements into a consistent or practical whole to form a new model or structure

Teaching type	Target level	Simple interpretation of connotation
Traditional teaching	Memory	Extract relevant information from long-term memory
	Understanding	Construct knowledge meaning from teaching information
Artificial intelligence assisted teaching	Application	Apply knowledge and skills learned in new situations
	Analysis	Decompose materials into elements, clarify the relationship between each element and the relationship with the whole
	Evaluation	Make value judgments on the learned knowledge and skills according to certain standards
	Create	Integrate all elements into a consistent or practical whole to form a new model or structure

The analysis dimension of the analysis framework of the inverted classroom teaching behavior of college sports based on artificial intelligence technology is mainly for the intelligent collection of early data in the actual analysis process, and then the evaluation dimension of the analysis data needs to be constructed. In order to scientifically determine the evaluation dimension of the framework, the author deeply analyzes the goal of college physical education inverted classroom teaching-efficient classroom evaluation. In order to ensure the scientific and comprehensive analytical framework of college physical education inverted classroom teaching behavior based on artificial intelligence technology.

In response to the issue of weight distribution, this study issued survey forms to experts. Finally, 11 effective survey forms are recovered. Hierarchical ordering is to obtain the maximum feature vector W of the judgment matrix by calculation, and then normalize W, and the value of the normalized W thus obtained is the corresponding influencing factor. On the basis of single-level ordering, the influence of all factors at the same level relative to the high-level is integrated, and the ranking of relative importance becomes the total ordering of the levels. In this study, one of the original matrices is selected for the calculation process of the index. $G = [\begin{matrix} 2 & 6 & 4 \\ 1 / 6 & 2 & 1 / 4 \\ 1 / 4 & 3 & 2 \end{matrix}]$ (1)

According to the above matrix, the normalized weight is W: $W = [0.64321, 0.120350.2123]$ (2)

In decision-making problems, a decision variable z is usually expressed as a linear combination of n variables x1, x2, …, xn, that is, z = w1x1 + x2w2 +... +xnwn, where wi > 0, w1,w2,..., wn are the variables x1, x2, …, xn. w = (w1, w2... wn) T is called a weight vector.

Suppose the judgment matrix is B = (bij) nxn, the specific calculation steps of calculating the sum product method of the eigenvectors of the judgment matrix are as follows:

Step 1: The elements in B are normalized by columns. $\bar{\bar{b_{ij}}} = \frac{{bi}_{j}}{\sum_{k = 1}^{n} {bk}_{j}}, (i, j) = 1, 2, 3 \dots \dots n$ (3)

Step 2: Add the columns of the same row of the normalized matrix. $\bar{w_{i}} = \sum_{k = 1}^{n} {\bar{\bar{b}}}_{ij} k_{j}, i = 1, 2, 3 \dots \dots n$ (4)

Step 3: Divide the added vector by n to get the weight vector, that is: $w_{i} = \bar{w_{i}} / n$ (5)

Step 4: Calculate the maximum feature root as: $η_{max} = \frac{1}{n} \sum_{i - 1}^{n} \frac{(Bw)_{i}}{w_{i}}$ (6)

2.3 Teaching mode construction

The inverted teaching mode consists of inverted practice, inverted classroom, inverted promotion and inverted evaluation, with the purpose of promoting deep learning. The whole teaching process is carried out under the support of the teaching environment, teaching resources and technical strategies. This model provides students with a mixed learning environment and teaching resources. One is the mixing of the real teaching environment and the virtual teaching environment. The second is the combination of online learning and offline learning relying on the inverted classroom. The third is the different characteristics of the course content. Resources are freely combined into teaching resources suitable for the course. Relying on the big data technology in the inverted classroom, it analyzes and judges students’ learning behaviors and habits, and helps teachers realize teaching according to their aptitudes as shown in Fig. 2. Students achieve advanced learning from imitation to innovation through self-practice, design, and creation. The close integration of various teaching stages enables students to gradually internalize the knowledge they have learned to achieve a higher target level and achieve deep learning [20 –24].

Based on artificial intelligence technology, the hierarchical relationship between the infrastructure layer, data layer and application layer and the order in which the analysis is carried out in the university sports inverted classroom teaching behavior analysis system. In the process of actual intelligent analysis, the purpose of the analysis should first be clear and combined. The analysis framework determines the analysis objects and analysis indicators, the video data resources obtained through the infrastructure layer, and the data layer classifies, cleans, and analyzes the data, and finally forms a visual chart to intuitively present to the users of the application layer. Inverted classrooms optimize new technologies for traditional classrooms, make full use of modern network, Internet, IOT, artificial intelligence and modern educational technology and other hardware equipment and software equipment. The junior middle school chemistry inverted classroom combines excellent teaching models to promote learners’ active learning methods and The teaching model is innovative, providing students with more comprehensive and extensive content, assisting students to master and absorb new content, and effectively improving the quality and level of education. And can teach according to the aptitude, according to the learner’s different characteristics, personality characteristics, learning habits and other personalized teaching mode, which help to help students of different levels to achieve the best individual learning level [24 –28].

Inverted classroom learning has increased interest in learning. Chemistry is always closely related to life. Chemistry is a colorful subject. Teachers use curriculum resources efficiently in inverted classrooms. Inverted systems display teaching so that students can experience the rich and colorful chemistry. Around, arouse students’ interest in learning. Teachers help students to build functional understanding of artificial intelligence technology, let students identify with inverted teaching, personally experience and feel the use of artificial intelligence, and inverted classroom belongs to each of them. Feeling the power of technology and science, it triggers students’ thinking about the chemistry in the study of chemistry, and cultivates students’ rigorous scientific spirit and core literacy.

3 Analysis of research results

3.1 Evaluation and analysis of teaching models

According to SPSS 25.0 software calculations, the value of the coordination coefficient of the first questionnaire is 0.492, and the degree of export coordination is medium. Because the indicators in the Delphi questionnaire of the first round are mainly based on the previous literature to determine the relevant dimensions and indicators, there will be unreasonable points, so the second round of Delphi law consultation is still needed. In order to obtain the reliability of the expert evaluation of the opinion consultation group, it is necessary to analyze the change and distribution of the importance of expert evaluation. Combined with the survey results of the opinion questionnaire, this study mainly calculated some representative statistics: the average and median used to measure the average state, as well as the standard deviation and the coefficient of variation of the volatility change state. The result analysis is shown in Fig. 3.

Fig. 2

Inverted artificial intelligence inverted college physical education classroom teaching.

Fig. 3

Statistics of questionnaire results.

In the example teaching video, a lecture takes 40 minutes. The teacher’s speech takes 30 minutes, and all the student’s speech takes 10 minutes. When analyzing the emotional data of the sample teaching video, the extracted speech data needs to be put into speech fragments. Speech data of different students are scattered and cannot correspond to the emotional analysis of the image data, and it cannot form a continuous visualization. The study analyzes the voice data of the entire example teaching video. First slices into speech segments at 30 s intervals. The sample video is close to 40 minutes, resulting in 80 text segments. Then, the text fragments are converted into word vectors, and the emotion recognition classification result through the emotion recognition network is shown in Fig. 4.

Fig. 4

Sentiment analysis results.

3.2 Teaching behavior analysis

Teachers combined with the feedback of the practice link, have a clear grasp of the students’ practice. Through statistics of the inverted classroom, the effectiveness of the inverted practice is judged from three aspects: the completion of the practice courseware, the completion of the practice test questions, and the discussion and communication. The statistical results of the completion of the practice courseware are shown in Fig. 5(a): 81% of the students completed the practice of the courseware, the average duration of use is 30 minutes, the autonomy is higher, and the completion is better. 12% of the students have only completed some of the courseware exercises, and the average duration is 10 minutes. Learning autonomy needs to be improved, and the completion is poor. 7% of students did not practice courseware. Their autonomy was poor, and their learning attitude was not serious. Judging from the completion of the practice courseware, the answer to the total score obtained is shown in Fig. 5(b). 27% of the students got full marks. 37% of the students answered a question incorrectly. This part of the student’s practice is more ideal, and the knowledge of this section is better. 15% of the students answered two questions incorrectly. This part of the students has mastered the basic knowledge, but there are some problems. The remaining 14% of the students are not very effective in practice, and there are many problems. It is necessary to focus on the problems encountered by these students in their studies.

Fig. 5

Physical education in colleges and universities.

In order to further analyze the mastery of the exercises, the error rate of each question is analyzed, as showed in Fig. 6. The error rate of the first two audio basic questions is relatively low, indicating that most students have a solid grasp of basic knowledge. The third question about the audio production process has an error rate of 19%, indicating that a small number of students have not fully mastered it. The fourth question examines the audio recording knowledge points with a higher error rate. The fifth question is regarding the audio effect editing has an error rate of up to 46%, indicating that most students have loopholes in this part of knowledge and cannot use it flexibly.

Fig. 6

Error rate distribution of physical education test questions.

From Fig. 7 we can clearly get the fluctuation trend of the emotions of teachers and students. According to the data of the emotional change graph, two indexes in the evaluation dimensions of the inverted frame of classroom teaching analysis based on artificial intelligence are selected: time and frequency, and then the positive emotion rate of teachers and students is calculated. Combining the obtained data. This study has designed an emotional score evaluation formula for experimental subjects. Inverted classroom teaching in college physical education is usually the case of a teacher against multiple students, so the formula for teachers and students will be different.

Fig. 7

Distribution of changes in emotional behavior.

From the above experiments and analyze results, it can be seen that the analytical framework of inverted classroom teaching behavior of college sport based on artificial intelligence technology is operable. However, due to the limitations of the current technology, it is not possible to clearly analyze the specific view of each student’s emotional change, and only the emotional evaluation score can be given from the overall classroom, and the corresponding positive results of the teacher and student emotional change visualization can be obtained respectively of emotional frequency and positive emotion rate.

3.3 Teaching effectiveness analysis

Establishing a set of classroom rules and regulations is essential for a good class, because it also directly or indirectly affects the quality of teaching. In the teaching time, the teacher can ask the student to gather at the playground or other classes places 5 minutes in advance. The sports committee or the class leader must borrow the equipment in advance, and cannot leave early, and the teacher must also does it. Before each class, teachers and students should conduct ceremonial negotiations, say hello to teachers and students, and remember attendance. Secondly, teachers should put forward requirements for students’ dress, including clothes and shoes must meet the most basic sportswear requirements for physical education. In the class, students are not allowed to start class discussions in private, observe class discipline, and do not interfere with or disrupt the normal order of classes and listen carefully. For difficult teaching, students can take notes. Finally, after the teacher completes the classroom summary, the students are required to return the equipment and count the equipment in time, because the school equipment is sometimes due to the negligence of the new teacher, causing some of the equipment to be lost. Students are required to consolidate and practice the content of all students after class, and practice the content of the next class in advance.

The survey (as showed in Fig. 8) found that in the evaluation of teachers’ effective allocation and efficient use of class time in teaching, 48% were satisfied, and 52% were dissatisfied. It can be seen that students are not very satisfied with the allocation and utilization of teachers’ class time. The effective allocation and efficient use of classroom time by physical education teachers need to be further improved and improved. Only three parts of the time are reasonably allocated according to the actual situation of students and schools, and efficient use can improve teaching efficiency.

Fig. 8

Evaluation results of effective allocation and efficient use of time in teaching.

According to the survey, the author found (as showed in Fig. 9) that in the evaluation of teachers’ ability to constantly reflect on their own teaching behavior and improve teaching, 53% were satisfied and 47% were dissatisfied. It can be seen that the student’s evaluation of teachers’ reflection on their teaching behavior is not high, indicating that teachers need to constantly reflect on teaching to effectively improve the teaching effect. If teachers do not reflect on their own teaching, they may lead to a lot of energy invested by the teachers, students’ learning is not high, motor skills are not formed, and teaching efficiency is low.

Fig. 9

Evaluation results of teaching behavior improvement teaching.

The suggestions of students for effective teaching deserve all our teachers engaged in physical education, because their opinions are the shadow of our teachers’ teaching. In fact, teaching is the same as we usually look in the mirror. We can’t just look at the students’ poor practice, but also need to take a look at places where we teach badly. The teacher-student relationship is crucial in teaching. To improve the teaching efficiency, teachers must improve the teacher-student relationship. Starting from this aspect, grasp the psychology of students, so that their hobbies can be carried out in class. Based on the relationship between teachers and students, coupled with their own efforts, the entire physical education classroom has become a real school. Teachers should be good at drawing lessons, and according to reasonable suggestions made by students, they can make reasonable adjustments to the teaching progress and plans, so as to be aware of them, and strive to stimulate students’ interest in learning, and promote the healthy and harmonious development of physical education.

This study designed the “3 + 1” inverted teaching model of inverted practice, inverted classroom, inverted promotion and inverted evaluation. The inverted teaching model was applied to the artificial intelligence college physical education course set up by the Master of Education. Finally, the effect of this practice was evaluated by the method of controlled experiment. In this study, the class with normal performance is basically used for comparison. Class A, which sets up a physical education teaching course in artificial intelligence colleges, is used as the experimental class, and class B is the control class. Experiment Class A uses the “3 + 1” inverted teaching model designed in this paper to teach, in order to verify the teaching effectiveness of this model. In contrast to Class B, the traditional teaching method is still used for theoretical and experimental classes. After the end of the semester course, class A and class B with the same initial conditions are compared and analyzed. Examination tests are conducted from two dimensions: test paper and micro-class work. The same test paper is designed for the exam. The teacher grades the micro video videos produced by the students at the end of the semester. The comparison results are shown in Fig. 10.

Fig. 10

Results comparison chart.

4 Conclusion

This thesis combines theoretical research and practical research methods to provide a new perspective on existing university sport behavior analysis and evaluation system of inverted classroom teaching. From the perspective of artificial intelligence technology-driven teaching, the aim is to build a scientific analysis framework for inverted classroom teaching in colleges and universities. They use artificial intelligence technology to reduce the repetitive and inefficient work of human analysis, and effectively improve the efficiency and quality of analysis of inverted classroom teaching behavior in colleges and universities. Promote diversified development of classroom evaluation methods, the development of teachers’ professional skills and the improvement of teaching quality. The value of the analytical framework for the inverted classroom teaching behavior of college sport based on artificial intelligence technology is mainly manifested in two aspects: 1) Efficient and intelligent real-time presentation of classroom status. Based on the analysis framework, it uses technology to participate in the analysis of college physical education inverted classroom teaching behavior, shorten the evaluation time, expand the evaluation dimension, and at the same time can feedback to teachers and students in real time, focusing on classroom effects in real time. 2) Regulate the inverted teaching behavior of college physical education. The evaluation of inverted PE teaching in colleges and universities has long paid attention to students’ academic performance, so as to judge whether the inverted PE teaching in colleges is effective. This research expands the dimensions and depth of analysis of the behavior of inverted classroom teaching in colleges and universities. At the same time, it saves manpower and visual display in the analysis process has obvious advantages compared with traditional analysis.

References

Abdel-Basset

, Manogaran

, Gamal

, Chang

, “A Novel Intelligent Medical Decision Support Model Based on Soft Computing and IoT [J], IEEE Internet of Things Journal.

Adekitan

A.I.

, Noma-Osaghae

, Data mining approach to predicting the performance of first year student in a university using the admission requirements [J], Education and Information Technologies 24(2) (2019), 1527–1543.

Aithal

P.S.

, Aithal

, Management of ICCT underlying Technologies used for Digital Service Innovation [J], International Journal of Management, Technology, and Social Sciences (IJMTS) 4(2) (2019), 110–136.

Boggs

S.D.

, Luedi

M.M.

, Nonoperating room anesthesia education: preparing our residents for the future [J], Current Opinion in Anesthesiology 32(4) (2019), 490–497.

Cao

, Wang

, Zhang

, et al., Command-filtered sensor-based backstepping controller for small unmanned aerial vehicles with actuator dynamics [J], International Journal of Systems Science 49(16) (2018), 3365–3376.

Chung

E.J.

, Lee

B.H.

, The effects of flipped learning on learning motivation and attitudes in a class of college physical therapy students [J], Journal of Problem-Based Learning 5(1) (2018), 29–36.

, Kumar

, Zeadally

, Vinel

, Yang

L.T.

, “Efficient and privacy-preserving data aggregation scheme for smart grid against internal adversariesm [J], IEEE Transactions on Smart Grid 8(5), 2411–2419.

Fantacci

, Picano

, “Federated learning framework for mobile edge computing networks [J], CAAI Transactions on Intelligence Technology 5(1) (2020), 15–21.

Gani

, Siddiqa

, Shamshirband

, et al., A survey on indexing techniques for big data: taxonomy and performance evaluation [J], Knowledge and Information Systems 46(2) (2016), 241–284.

10.

Guo

, Analysis on Influencing Factors of Dance Teaching Effect in Colleges Based on Data Analysis and Decision Tree Model [J], International Journal of Emerging Technologies in Learning (iJET) 15(09) (2020), 245–257.

11.

Hung

C.Y.

, Sun

J.C.Y.

, Liu

J.Y.

, Effects of flipped classrooms integrated with MOOCs and game-based learning on the learning motivation and outcomes of students from different backgrounds [J], Interactive Learning Environments 27(8) (2019), 1028–1046.

12.

Kim

, Ke

, Effects of game-based learning in an OpenSim-supported virtual environment on mathematical performance [J], Interactive Learning Environments 25(4) (2017), 543–557.

13.

Kloos

C.D.

, Alario-Hoyos

, Muñoz-Merino

P.J.

, et al., Educational Technology in the Age of Natural Interfaces and Deep Learning[J], IEEE Revista Iberoamericana de Tecnologias del Aprendizaje 15(1) (2020), 26–33.

14.

Kong

, Innovative applications mode of network learning space in exercise physiology based on ubiquitous learning [J], International Journal of Emerging Technologies in Learning (iJET) 14(04) (2019), 113–126.

15.

Kong

, Bai

, Kong

, Innovative Flipped Classroom Strategy by Computational Thinking [J], Advances in Educational Technology and Psychology 2(1) (2018), 252–257.

16.

Limniou

, Schermbrucker

, Lyons

, Traditional and flipped classroom approaches delivered by two different teachers: the student perspective [J], Education and Information Technologies 23(2) (2018), 797–817.

17.

Mustafa

, Abbas

M.A.

, Hafeez

, et al., Effectiveness of ontology-based learning content generation for preschool cognitive skills learning [J], Interactive Learning Environments 27(4) (2019), 443–457.

18.

Naidoo

G.M.

, Madida

, Rugbeer

, Conceptual framework for ICT integration in rural secondary schools in South Africa[J], Journal of Gender, Information and Development in Africa (JGIDA) 8(3) (2019), 187–212.

19.

Natural language interface model for the evaluation of ergonomic routines in occupational health (ILENA), Moya Jutinico Carlos Julio, Montenegro-Marin Carlos Enrique, Burgos Daniel, González Crespo Ruben [J], Journal of Ambient Intelligence and Humanized Computing 10 (2019), 1611–1619.

20.

21.

Prathik

, Anuradha

, Uma

, “Survey on Spatial Data Mining, Challenges and Its Applications [J], Journal of Computational and Theoretical Nanoscience 15(9-10) (2018), 2769–2776.

22.

Tang

, Learning Mechanism and Function characteristics of MOOC in the process of higher education [J], Eurasia Journal of Mathematics, Science and Technology Education 13(12) (2017), 8067–8072.

23.

Wang

S.Y.

, Chang

S.C.

, Hwang

G.J.

, et al., A microworld-based role-playing game development approach to engaging students in interactive, enjoyable, and effective mathematics learning [J], Interactive Learning Environments 26(3) (2018), 411–423.

24.

Wazid

, Das

A.K.

, Kumar

, Conti

, Vasilakos

A.V.

, A novel authentication and key agreement scheme for implantable medical devices deployment [J], IEEE Journal of Biomedical and Health Informatics 22(4) (2018), 1299–1309.

25.

J.Y.

, Hsiao

Y.C.

, Nian

M.W.

, Using supervised machine learning on large-scale online forums to classify course-related Facebook messages in predicting learning achievement within the personal learning environment[J], Interactive Learning Environments 28(1) (2020), 65–80.

26.

Cao

, Jia

, Gunasekaran Manogaran, “Efficient Traceability Systems of Steel Products Using Blockchain-based Industrial Internet of Things [J], IEEE Transactions on Industrial Informatics.

27.

Yoon

S.Y.

, Student Readiness for AI Instruction: Perspectives on AI in University EFL Classrooms [J], Multimedia-Assisted Language Learning 22(4) (2019), 134–160.

28.

Yue

, Zou

, Online Teaching System of Sports Training Based on Mobile Multimedia Communication Platform [J], International Journal of Mobile Computing and Multimedia Communications (IJMCMC) 10(1) (2019), 32–48.