Research on the Innovative Path of Intelligent Technology-Enabled Curriculum Design in the Process of High-Quality Development of Higher Education

In the process of high-quality development of higher education, intelligent technology-enabled curriculum design has the following important significance:

This paper takes the artificial intelligence branch of intelligent technology as the intrinsic driving force, and carries out construction and exploration after closely integrating it with higher education courses, and the driving process is in order: optimizing the course objectives, empowering course design and implementation, and perfecting course assessment and evaluation in three steps.

2.2.2

Artificial Intelligence Enabled Curriculum Design and Implementation

Driven by the curriculum objectives of knowledge, competence, and quality, AI technology has provided powerful momentum to the design and implementation of the curriculum. Given the inclusiveness and extensibility of artificial intelligence, it is easy to realize the cross-discipline. The specific steps of artificial intelligence to empower the process of curriculum design and implementation in colleges and universities are shown in Figure 1.

Figure 1.

The steps of empowering course design with AI

Step 1: Mining materials

First, use data mining algorithms and big data technology in the context of artificial intelligence, combined with the content of the course teaching and the mining of course materials.

Step 2: Building a library of materials

Under the premise of the first step, teachers play the role of “cleaning”, screen the materials for the first time under the guidance of the curriculum objectives, remove the content with negative guiding influence, unclear values, and contrary to the development trend of the content, and then use database technology to establish a course material library, and at the same time supplement the new teaching content with the latest research results and application technologies in the field of artificial intelligence.

Step 3: Classroom Integration

Give full play to the role of the material, integrate it into the classroom naturally and effectively, create a vivid and novel teaching environment with the assistance of relevant intelligent equipment, teachers organically arrange the chapter process, effectively control the classroom rhythm, the process always emphasizes the students’ understanding of the principles, methods, realization techniques, development trends and other aspects of the integration and implementation of the final.

Step 4: Updating materials

According to the classroom feedback and timely reflection on the teaching design, improve and update the teaching case again, through the feedback to constantly modify the data mining model, the formation of the teaching material library of self-adaptation, to improve its perception, and to explore more accurate material to stimulate the students’ desire to explore the knowledge.

2.2.3

Artificial Intelligence Improves Course Assessment and Evaluation

This subsection combines the design and implementation of the course, the artificial intelligence technology combined with computer vision, database and other technologies applied to the course of the various assessment links, echoing the trinity of the course objective pattern, making the evaluation links more vivid and relevant, rich and complete. In addition, artificial intelligence technology is more relevant to the actual teaching data while relieving the teachers’ work pressure, which helps to form a more perfect way of multiple evaluation of the course. The specific application process of artificial intelligence in course assessment is shown in Figure 2.

Figure 2.

The application of AI in course assessment

In order to achieve the high-quality development of higher education, this paper optimizes the intelligent technology-enabled curriculum design and implementation environment, and proposes the innovative path shown below:

The t test, as the most basic of the statistical inference methods for continuous variables, is mainly used for normally distributed information with a small sample size (e.g., n < 30) and an unknown overall standard deviation σ [20].

t The test gives the following 2 possible hypotheses:

H₀: u = u₀ that the sample mean is not significantly different from the assumed overall mean, and that the difference that exists is due entirely to sampling error.

H₁: u ≠ u₀, The sample mean is significantly different from the assumed overall mean and the difference that exists does reflect this difference in addition to being caused by sampling error.

t The test utilizes the characteristics of the T-distribution and uses t as the test statistic to perform the test, with the specific statistical expression: (1) t=X¯−μ0sX¯=X¯−μ0s/N,Degree of freedom df=N−1 $$t = {{\bar X - {\mu _0}} \over {{s_{\bar X}}}} = {{\bar X - {\mu _0}} \over {s/\sqrt N }},{\rm{Degree}}\,{\rm{of}}\,{\rm{freedom}}\,df = N - 1$$

t Tests include one-sample t tests, independent sample t tests, and paired-sample t tests. The one-sample t test is used to compare a sample’s data with the overall mean. The independent samples t test is used to compare the means of 2 groups of samples. The Paired Samples t test is used to compare the means of groups of data, where there are as many groups as there are pairs of data, and where there is some correlation between the pairs of data.

The Paired Samples t test is used to test whether paired samples come from a normal population with the same mean. The basic principle is to obtain the difference of each pair of data: if the treatment factor has no effect on each pair, the mean of the difference is equal to 0, and the mean of the samples drawn from the totals in which the paired samples are drawn should fluctuate around 0. Conversely, if the treatment factor has an effect on each pair of data, the mean of the difference is not equal to 0, and the sample mean drawn from the population in which the paired samples are located is farther away from 0 [21].

In the paired samples t-test, let x₁,x₂(x = 1,2,…n) be the paired samples respectively. Its sample difference d_i = x₁ − x₂, at which point the test statistic: (2) t=d¯−(μ1−μ2)S/N where d¯ is the mean of d_i, S is the standard deviation of d_i, and N is the sample size. When μ₁ − μ₂ = 0, the t-statistic obeys a t-distribution with N-1 degrees of freedom.

In fact, the paired-sample t-test is also the one-sample t-test for the difference. And the conditions for the applicability of the one-sample t-test, according to the central limit theorem, even if the original data do not obey a normal distribution, as long as the sample size is large enough, then the sampling distribution of the sample mean is still normal. So as long as the distribution of the data is not strongly skewed, the t-test is generally applicable.

In order to explore the effectiveness of the innovative path of intelligent technology-enabled curriculum design, this paper takes the design of public physical education courses in colleges and universities as the research object, and selects the students of public physical education courses in H colleges and universities as the experimental sample. Among the four classes totaling 240 students that can be studied, two classes with 120 students and 60 students in each class are randomly selected, one is the control group (32 female students and 28 male students), and the other is the experimental group (31 female students and 29 male students), and the experimental study of their teaching is carried out through 16 weeks of class time. The experimental group used the innovative approach of this paper for course content design, while the control group used the traditional approach for course design. The experimental measurement indexes include physical fitness level and attitude towards physical activity. Physical fitness levels are obtained through a physical fitness test, and physical activity attitudes are scored through a questionnaire.

Before and after the experiment, the students in the experimental group and the control group were tested for their corresponding physical health level, including lung capacity, 50m, standing long jump, seated forward bending, 800m/1000m, and pull-ups/sit-ups. In terms of questionnaire distribution, among them, the evaluation indexes of physical activity attitudes included behavioral attitudes, goal attitudes, behavioral cognition, behavioral habits, behavioral intentions, emotional experience, sense of behavioral control, and subjective standards. The Cronbach’s alpha coefficient of the questionnaire scale was 0.914>0.7, the KMO value was 0.895>0.8, the p-value of the Bartlett’s test of sphericity was 0.000<0.05, and the explained rate of the rotated cumulative variance was 85.79%>50%, which indicated that the scale had good reliability and validity.

Independent samples t-test was conducted on the physical fitness level of the experimental group and the control group before the experiment, and the results of the independent samples t-test on the physical fitness level before the experiment are shown in Table 1.

As can be seen from Table 1, the independent sample t-test P-value of the performance of the experimental group and the control group in the six test items of lung capacity, 50m, standing long jump, seated forward bending, 800m/1000m, and pull-ups/sit-ups before the experiment is greater than 0.05, which indicates that there is no significant difference between the experimental group and the control group in the physical fitness level before the experiment and they have chi-square sex.

The results of independent samples t-test of physical fitness level of experimental and control groups after the experiment are shown in Table 2.

As can be seen from Table 2, the independent samples t-test P-values of the performance of the experimental group and the control group in the six test items of lung capacity, 50m, standing long jump, seated forward bending, 800m/1000m, and pull-ups/sit-ups after the experiment are 0.032, 0.006, 0.021, 0.046, 0.009, and 0.015, respectively, which are all less than 0.05, and there is a significant difference. It indicates that the course design based on an intelligent technology-enabled innovation pathway in this paper is significantly better than the traditional course design, and the teaching effect is better.

The results of the paired-samples t-test for the physical fitness level of the control group before and after the experiment are shown in Table 3. As can be seen from Table 3, there is no significant difference in the six dimensions of physical fitness level of the control group before and after the experiment (P>0.05), which indicates that there is no significant improvement in the physical fitness level of the control group before and after the experiment, i.e., the effect of the public physical education program designed according to the traditional method on the enhancement of the physical fitness level of students is not significant.

The paired-sample t-test results of the physical fitness level of the experimental group before and after the experiment are shown in Table 4. As can be seen from Table 4, the P-value of the experimental group’s performance in each physical fitness level test item is less than 0.05, indicating that there is a significant difference in the physical fitness level of the experimental group before and after the experiment, which corroborates the validity of the path of course design in this paper.

The independent sample t-test of physical activity attitudes of the experimental group and the control group was conducted before the experiment, and the results of the independent sample t-test of physical activity attitudes before the experiment are shown in Table 5.

As can be seen from Table 5, there is no significant difference between the experimental group and the control group before the experiment at the level of eight indicators: behavioral attitude, goal attitude, behavioral cognition, behavioral habits, behavioral intention, emotional experience, sense of behavioral control, and subjective standards (P>0.05), indicating that the physical activity attitudes of the experimental group and the control group before the experiment are more or less the same.

Immediately after the course, a physical activity attitude questionnaire was administered to both groups of students. Students in the control group were tested with the physical activity attitude questionnaire, and the data obtained from the two questionnaire distributions were analyzed using the paired samples t-test. The results of the paired samples on the experience of physical activity attitudes of the control group are shown in Table 6.

As shown in Table 6, after one semester of traditional teaching, among the eight indicators of physical activity attitude of the control group students, there are significant differences in the four indicators of behavioral attitude, behavioral habits, behavioral intention and behavioral sense of control (P<0.05), and there are no significant differences in the target attitude, behavioral cognition, affective experience and subjective criteria (P<0.05), but the comparison of scores before and after shows that all of them are slightly higher than the scores before teaching after teaching. .

Similarly, the paired-samples t-test results of the physical activity attitudes of the experimental group measured before and after the experiment are shown in Table 7.

As can be seen from Table 7, there is a significant difference between the eight dimensions of physical activity attitudes of the experimental group before and after the experiment (P<0.05), and when comparing their means, the mean value after the experiment is significantly higher than that before the experiment. This indicates that the physical education learning attitude of the experimental group was significantly improved before and after the experiment.

To further validate the experimental results, an independent t-test was conducted on the physical activity attitudes of the experimental and control groups after the experiment. The results of the independent sample t-test on physical activity attitude after the experiment are shown in Table 8.

As can be seen from Table 8, the p-values of the experimental group and the control group in the eight physical activity attitude indicators of behavioral attitude, goal attitude, behavioral cognition, behavioral habits, behavioral intention, emotional experience, sense of behavioral control, and subjective standards after the experiment were 0.024, 0.002, 0.041, 0.038, 0.000, 0.000, 0.004, and 0.009, respectively, which were all less than 0.05, there is a significant difference. In summary, it can be seen that the intelligent technology-enabled curriculum design innovation path designed in this paper can effectively improve students’ attitudes toward physical exercise, thus promoting the enhancement of students’ physical fitness and health, and the effect is significantly better than the traditional curriculum design path.