Abstract
In order to improve the effect of college English classroom teaching, this paper combines optical recognition to improve machine vision algorithms and uses computer optical vision technology to process teaching images. The system designed in this paper can be applied to philosophical teaching in college English classrooms. Moreover, the system can optimize teaching resources, manage teaching classrooms through the improved machine vision algorithm in this paper, and have a formative evaluation effect. In addition, taking into account the psychological activities of students in the classroom, this paper integrates the emotional recognition of college students in the construction of the system. Furthermore, it combines the actual teaching process to build a college English classroom teaching system based on constructivism. Finally, this paper designs an experiment to analyze the effect of the teaching model. From the research results, it can be known that the teaching system meets the demands of teaching.
1. Introduction
Under the background of the integration of the world economy, the role of English for college students is self-evident. The continuous advancement of information technology promotes the change of English teaching methods. Currently, many computer-assisted technologies are applied to university classroom teaching. However, although most universities use computer-assisted technology for online college English teaching, they are still affected by traditional teaching models. Moreover, computer-assisted English online teaching still has certain drawbacks, which affect teaching efficiency, so it needs to be improved [1]. Constructivism is a theory of learning which is further developed after the enhancement of activism to cognitivism. In addition, constructivism is a process in which learners spontaneously construct internal mental representations. In addition, the constructivist does not impart to learners the theoretical knowledge that subverts the tradition. However, learners gain from the active construction of meaning with the help of teachers, learning partners, or other people under a specific social and cultural background [2].Therefore, in education based on constructivist learning theory, providing learners with an appropriate learning environment and building a new relationship between teachers and students are the two most important aspects.
Constructivism advocates artistic conception learning, which is learning through target-oriented activities in the real application environment of the learned knowledge. The cognitive flexibility theory advocated by them is to develop learners’ cognitive flexibility and form a multifaceted understanding of knowledge. Therefore, knowledge learning should be combined with specific conditions. By entering the state of rearrangement multiple times, learners can form background experience, master the complexity of knowledge and related relationships, and then use actual learned knowledge to solve real-life problems [3]. This article combines constructivism to play computer-assisted technology in college English classrooms. It constructs an efficient teaching system that can be used for college English teaching and conducts system performance analysis through experimental research.
The rest of the article is composed as follows. In Section 2, related work is studied. In Section 3, online teaching text recognition is elaborated, followed by the college English classroom teaching system based on constructivism in Section 4. The results are given in Section 5, and the article is concluded in Section 6.
2. Related Work
There are many researches on intelligent computer teaching systems. This article summarizes the application of computer-aided technology and artificial intelligence technology in college teaching, as follows: the literature [4] comprehensively analyzed the current situation of artificial intelligence education. According to its investigation, there are problems in implementing artificial intelligence courses, and there is no real teaching system. The literature [5] more specifically analyzed the shortcomings and problems of current artificial intelligence teaching materials for marketing. It believes that the difficulty of hardware is temporary. With the further development of computer technology, the price of neural computing power required for artificial intelligence-related research has also fallen sharply. The literature [6] studied the model of AI education and pointed out that AI education is mainly embodied in acupuncture preparatory courses or many fee-charging educational institutions, programming seminars, or training camps. The literature [7] conducted more profound research on case-based teaching in AI teaching and classified it into three types: model reference, question reexamination, and game reasoning. The literature [8] put forward specific corresponding opinions on different stages of artificial intelligence curriculum education. According to the different textbooks, the focus of some researchers is also different. The literature [9] discussed using problem-solving education strategies in artificial intelligence education with robot control as the content. In the literature [10], the effect of game case law is studied.
The literature [11] studied the design and implementation of a personalized learning navigation system based on data mining, introduced an adaptive organization into the distance education system, and realized personalized learning navigation according to the characteristics of learners. The literature [12] designed a multiagent-based intelligent distance education environment to realize the intelligence and adaptability of the distance education system. The literature [13] studied adaptive derivative systems and authoring tools. According to technologies in the fields of intelligent education systems, hypertext, user models, etc., it constructed a user’s knowledge model based on the interactive information between the user and the system.
Finally, the literature [14] designed a student characteristic analysis system in a network environment. Through collecting and analyzing the dynamic and static information in the student’s learning process, it proposed a theoretical module for designing the learner characteristic analysis system. The literature [15] comprehensively applied workflow technology, computer collaboration technology, data mining technology, and intelligent agent technology to intelligent education systems to realize automatic reasoning, automatic delivery of personalized learning information, teaching decision support, and various educational workflows. The literature [16] developed a personalized intelligent education system. When students can attend classes normally, in order to improve their problem-solving ability and master knowledge, they can practice in this system.
3. Online Teaching Text Recognition
The algorithm proposed in this paper is mainly used for font recognition in network teaching. Therefore, image recognition technology needs to be applied, and the recognition process needs to be combined with optical technology.
The scalar wave equation can be expressed as follows [17]:
The definition of the algorithm parameters is as follows: the refractive index of the medium is , the speed of light in a vacuum is , and the complex amplitude of the light field is . Then, there are
In the formula, the wave vector is , and is the angular frequency of the light wave. When there is a point source at position , the solution of the above formula is called Green’s function , that is [18],where characterizes the spatial impulse response of the point source at a position at . When multiplying it with any incident light field , we have
The incident surface is denoted as . From the above formula, it can be concluded that the incident light field is the sum of the light field contributions of different positions in the incident light field [19].
In the formula, is the response of the light field at a position at , which is the Green’s function of the random scattering medium. The above formula can be discretized as
Among them, is the amplitude of incident channel a, and is the phase of incident channel a. The complex coefficient is a set of N weight coefficients, representing the transmission relationship of light waves from each channel a to channel b.
The complex coefficient of the light field relationship can be expressed as , and the corresponding complex matrix is called the optical transmission matrix. Then, the transfer matrix model can be expressed as
Among them, and are the light fields of the -th incident channel and -th exit channel, respectively, and is the element in the transmission matrix [20].
In the feedback wave front shaping experiment, the network English text configuration diagram before the optimization is shown in Figure 1. In the picture, we can see speckle particles shaped like “caterpillars.” Because the central brightness of the speckle particles is high and the peripheral brightness is low, speckles are formed randomly distributed in the light and dark particle positions.
The complex amplitude corresponding to the -th output channel can be expressed as
In the above formula, and are the amplitude and phase of the -th incident photon through the scattering medium, and and are the amplitude and phase of the -th output channel, respectively. Here, the superposition process of this complex amplitude is explained with a simple example. Figure 2(a) shows a schematic diagram of long-phase interference. The speckle pattern in the speckle pattern is obtained by the interference of the phase length of each light wave vector. Therefore, the thin-line light wave vector approximated in the four directions in the complex plane is the long thick-line vector obtained by the overlap of the phase length. Thus, the length of the line is the amplitude dimension.
(a)
(b)
On the contrary, Figure 2(b) shows a schematic diagram of interference cancellation. The dark speckle is obtained by canceling the interference of each light wave vector. The thin-line light wave vectors with larger differences in the four directions in the complex plane are canceled and superimposed to obtain a shorter thick-line vector.
Two discriminants are designed, which are expressed in the following form:
Among them, is the number of focus points, is the background average intensity of the output light field, and is the standard deviation of the intensity of focus points.
The discriminants of and are respectively written as
They satisfy the following relationship:
The above formula satisfies the following properties:
and the equal sign holds only when .
Among them, ; it characterizes the intensity value of m focal points.
First, the auxiliary conclusions are introduced: if , then , and the equal sign holds only when .The binomial expansion can prove this lemma
The original proposition is equivalent to
The equal sign holds only when .(1)When , the proposition obviously holds. After expanding by , it is easy to get .(2)We assume that the proposition holds when , that is, , and the equal sign holds only when . Then, when , if is the largest of , then there is , and the condition for taking the equal sign is . If we set , then there is .
According to the lemma, we can get
If and only if , that is, , the equal sign holds. Therefore, for , holds, that is, the original proposition is proved.
If we set , then . Figure 3 shows the relationship between and f in these two discriminants.
From Figure 3, we can see that the curves of and are a straight line and a parabola, respectively. In order to make the enhancement factor f as large as possible, there are endless combinations of feasible solutions for (such as , or ), but there is only one perfect feasible solution for .
4. College English Classroom Teaching System Based on Constructivism
This article is to verify the English classroom teaching system under the background of constructivism. The teaching system of this paper needs to use computer optical vision technology for teaching image processing. Therefore, in the construction of the teaching system, the computer-aided technology system is constructed through the proposed scheme. This paper takes students as the center in the system research, so this paper takes students as the teaching center when constructing the system. Based on constructivism, the instructional design process is shown in Figure 4.
The application of artificial intelligence technology to college English teaching needs to be combined with the actual teaching process. The intelligent feedback system of college English teaching constructed in this paper is shown in Figure 5.
The system designed in this paper can be applied to philosophical teaching in college English classrooms. The system can optimize teaching resources, manage teaching classrooms through the improved machine vision algorithm in this paper, and have a formative evaluation effect. Moreover, the system constructed in this paper also has a database function, which can continuously optimize the teaching process and eliminate problems in teaching. In addition, as the teaching continues to deepen, the system will be continuously improved, and the teaching effect will also be improved. The database constructed in this paper has multiple functions such as data input, output, and data processing. It is based on an embedded structure and has strong scalability.
While constructing a college English classroom intelligent teaching system, this paper considers students’ mental activities in the classroom. Also, this paper incorporates the emotional recognition of college students in the construction of the system. The curve of the psychological emotion recognition model constructed in this paper is shown in Figure 6, which shows the theoretical curves of three levels of difficulty. In order to improve the effectiveness of system emotion recognition, an optical vision algorithm is applied to classroom student emotion recognition. It makes the algorithm model constructed in this paper more intelligent. At the same time, teachers can effectively adjust classroom teaching strategies according to the system recognition results.
A constructivist-based intelligent teaching system for college English is constructed by integrating emotion recognition into college English teaching, as shown in Figure 7.
5. Performance Analysis of the Proposed System Based on Constructivism
After constructing the intelligent teaching system of college English based on constructivism, the performance verification and analysis of the system are carried out. According to the actual needs of English teaching, this paper mainly starts with two aspects of English character recognition and student emotion recognition when constructing the system. Moreover, this paper uses video and image English character recognition to acquire and process teaching resources effectively and uses emotion recognition to facilitate the real-time formulation of classroom teaching methods, which will help improve teaching efficiency and help students grasp English knowledge quickly and in a effective manner.
In the English teaching experiment, this paper evaluates the system performance through two sets of experiments. One group evaluates the English character recognition effect based on the improved optical machine vision algorithm, and the other group evaluates the student’s emotion recognition effect. First of all, this paper conducts automatic character recognition in an English classroom. Through automatic English recognition, teaching content can be delivered to students promptly. This method is also convenient for teachers to obtain teaching resources promptly. Then, the English character recognition effect of the system constructed in this paper is evaluated. The outcomes are as shown in Table 1 and Figure 8.
From the abovementioned research, we can see that the intelligent teaching system of college English based on constructivism has a perfect result in English character recognition. On this basis, this paper further researches and analyzes the effect of the system on student emotion recognition. The outcomes are as shown in Table 2 and Figure 9.
From the abovementioned chart analysis, we can see that the intelligent teaching system of college English based on constructivism has an excellent result in student emotion recognition. The system meets demands, and the system constructed in this paper can be used for practical teaching in subsequent experimental teaching.
6. Conclusion
The current English teaching method is relatively single. The teaching process still uses the traditional teaching mode, so the teaching mode still has certain drawbacks. This paper uses computer-assisted technology in college English classrooms to construct an efficient teaching system based on constructivism. It can be used for college English teaching and conducts system performance analysis through experimental research. The proposed model is mainly used for font recognition in network teaching, so it needs to apply image recognition technology. Furthermore, the recognition process needs to be combined with optical technology for research.
Moreover, by improving machine vision, English characters can be effectively recognized in English classroom teaching, which allows teachers to collect and send teaching resources. It is convenient for students to take notes in time. In addition, this paper mainly starts with two aspects of English character recognition and student emotion recognition when constructing the system. First, this article uses video and image English character recognition to acquire and process teaching resources effectively. Second, it also uses emotion recognition to facilitate the real-time formulation of classroom teaching methods. It will help improve teaching efficiency and help students grasp English knowledge quickly and effectively. From the experimental research results, we can see that the method proposed in this paper has certain feasibility.
Data Availability
The data used to support the findings of this study are available from the author upon request.
Conflicts of Interest
The author declares no conflicts of interest.
Acknowledgments
This study was supported by Teaching Reform and Research Project of Xijing University in 2019 (No. JGGH1904).