Human-computer interactive teaching model based on fuzzy set and BP neural network

Abstract

As the main channel of human-computer communication, multimedia education technology can realize the virtualization of education and multi-dimensional information. In this paper, the authors design a human-computer interactive English experience teaching based on fuzzy set and BP neural network. With the development of intelligent education, the improvement of English teaching quality is particularly important, especially the effectiveness of classroom teaching. The construction of interactive education system has changed the traditional classroom teaching mode and made it possible for individual autonomous learning. This English teaching system is an E-learning platform based on network updating. The E-learning system has the following advantages: (1) E-learning media is easy to update, can provide more teaching content, and provide convenience for teaching. (2) E-learning interaction can stimulate learning interest; (3) E-learning is rich in educational materials and easy to set teaching objectives. (4) Using E-learning’s human-computer interaction function, we can strengthen the supervision of education and teaching process.

Keywords

Fuzzy set human-computer interaction English teaching evaluation model

1 Introduction

With the increasing popularity of such concepts as “global village”, “WTO” and a variety of world-class events in China’s development, effective communication has become the focus of today’s education [1, 2]. To a certain extent, the new technology has deeply influenced the development of education, communication and media. At the same time, the development of education has promoted the progress of people’s life and accelerated the renewal of social civilization. Especially in the background of today’s rapid development of information technology, the use of new teaching tools has become a significant part of current teaching. Cross-cultural education is not only the requirement of social development in the twenty-first century, but also has become one of the major goals of college students’ teaching [3]. Language is regarded as a tool for the exchange of spiritual and ideological elements and provides the understanding and communication channel for our daily life. English, as a universal language, is an important medium to realize the efficient communication between people all over the world [4]. At present, eighty percent of the world’s information is stored in English, more than half of the world’s scientists can communicate in English, and fifty percent of the world’s academic journals are published in English. Today, English is not only a communication tool, but also is an important means of national and international influence. English education is an educational program that can adapt to the international trend and help people communicate smoothly in their daily life and work. The English culture education for college students has made an important contribution to the cultivation of English and its related talents. The experiential teaching of college students’ English culture can be realized by using the new technology, which is the most important of the current teaching methods. The era of digitization also puts forward higher standards for the education of college students [5]. Students, in the context of English culture, get the effective knowledge and skills to strengthen the cultural and economic exchanges. Moreover, the English learning class in China’s college also enable students to have some contacts with the western literature and culture. Thus, finding a suitable way for college students is inevitable in the teaching of College English in China [6].

The main contribution of this paper is to design a human-computer interactive English experience teaching based on fuzzy set and BP neural network. With the development of intelligent education, the improvement of English teaching quality is particularly important, especially the effectiveness of classroom teaching. The construction of interactive education system has changed the traditional classroom teaching mode and made it possible for individual autonomous learning.

This paper is organized as follows: The related work is introduced in Section II. BP neural network and error revision method is described in Section III. Cloud computing and education is presented in Section IV and case analysis and Judgment matrix of AHP is presented Section V. Finally, Conclusions are given in Section VI.

2 Related work

Since 1960 s, the United States has been the first to study the experiential teaching. And as of 1980 s, the United States carried out three conferences on thematic studies [7]. In 1990 s, the primary role of culture teaching in the education sector was established, while the main communication targets of interpersonal communication, interpretation and presentation were established. Meanwhile, other subject targets of cultural practices and goals of comparative language and culture were obtained. Based on those above-mentioned standards, they could get the information, emotional expression and exchange of views in the experiential teaching of English culture, while understanding the written and spoken communications, and cultural products [9, 10]. They agreed with others, understood the nature of language, and enriched themselves with lifelong learning [11 –13]. Now, the United States has made a thorough and comprehensive study on the experiential teaching, and has carried on the fruitful discussions at different levels.

European Studies of cultural experiential teaching began in the Second World War, especially after the establishment of the European Union, when international exchanges and cooperation were much closer. The teaching of communicative approach has become a new teaching method (Peng, 2010). The recent research in literature and language teaching was more was more thorough and proposed the following ability and objectives related to language, including comprehensive ability, communicative ability, declarative knowledge, survival skills, social linguistic competence and pragmatic competence [14 –16]. The aims are the cultural knowledge of the world, the strengthening of practical skills, the establishment of correct learning attitude and motivation, the improvement of language and communication awareness, the shaping of learning skills and satisfactory expression of all kinds of verbal communication tasks [17].

The experiential teaching in China is in a more cautious stage. There are also some books and papers on culture teaching in class. But the situation is more fragmented, as there is no systematic and overall planning [18 –20]. As early as in the Warring States period, the university education already emerged in our country. In the thirteenth century, Western Europe also produced a modern university [8]. In 1980 s, the relevant scholars of our country had made some researches and discussions about the experiential teaching, and put forward the content, principle and method of culture teaching [21]. Although the study of English culture teaching has been put forward, the main difficulty is dialectical thinking, and there is no further research and discussion. As far as the students are concerned, most students don’t realize the main purpose of learning English. In the process of English learning, the interest remains weak, and English has not been greatly improved [22 –24]. As far as teachers are concerned, they are not clear about what the teaching is, since there is no effective way and method of teaching to improve classroom efficiency and to meet the needs of the students [25]. The study of English experiential teaching in our country is not thorough, so huge challenges lie ahead for experiential teaching [26, 27]. Meanwhile, the localization of English itself makes the emergence of a large number of “Chinglish”. There are differences in the linguistic competence, communicative competence, and cross-cultural perspective.

3 The establishment of model

3.1 AHP method

AHP is established by the hierarchical structure model, contrast matrix is built, the index weight is calculated, and consistency test is made to get the weight value of the index. And then the result is compared. Specific processes are as follows:

Target level division

Usually the level is divided into three layers. A represents the target layer, the layer B represents the middle layer, the layer C represents the underlying layer. The top level is actually the expected goal of research topics. The middle layer is actually one or some of the intermediate processes that are done according to the specific situation. The lowest level is actually the specific measures and perspectives. Hierarchical structure as shown in Tables 1 –3.

The construction of layer B to the layer A contrast matrix

The determining of judgment matrix $A = [\begin{matrix} a_{11} & a_{12} & \dots & a_{1 n} \\ a_{21} & a_{22} & \dots & a_{2 n} \\ a_{31} & a_{32} & \dots & a_{3 n} \\ a_{n 1} & a_{n 2} & \dots & a_{nn} \end{matrix}]$ (1)

Weight vector ɛ (A) = (ɛ₁, ɛ₂, ɛ₃, ⋯ , ɛ_n) is got. $ɛ = \frac{\sqrt{\prod_{j = 1}^{n} a_{ij}}}{\sum \sqrt{\prod_{j = 1}^{n} a_{ij}}}$ (2)

Consistency check

RI represents consistency index.

Maximum eigenvalue is: $λ = \frac{1}{n} \sum_{i = 1}^{n} \frac{{(A ɛ)}_{i}}{ɛ_{i}}$ (3) Judgment matrix order $CI = \frac{λ_{n} - n}{n - 1}$ (4) Consistency ratio is got. ${CR}_{A} = \frac{CI}{RI}$ (5)

The judgment matrix of the level B and the level C is as follows.

B is two level evaluation indices.

Two level index consistency ratios is: ${CR}_{B} = \frac{\sum_{i}^{n} ɛ_{i} {CI}_{i}}{\sum_{i}^{n} ɛ_{i} {RI}_{i}}$

Table 1

Scaling

	1	2	3	4	5	6	7	8	9
Importance	1	1.5	2	2.5	3	3.5	4	4.5	5

Table 2

RI Index distribution table

Program	Index
N	1	2	3	4	5	6	7	8	9
RI	0	0	0.42	0.85	1.11	1.26	1.35	1.48	1.51

Table 3

Right target layer and the second-stage evaluation of the weight value

	A ₁	A ₂	⋯	A _n	Weights
	ɛ ₁	ɛ ₂	⋯	ɛ ₃
B ₁	q ₁₁	q ₁₂	⋯	q _1n	$\sum_{j = 1}^{n} ɛ_{j} q_{1 j}$
B ₂	q ₂₁	q ₂₂	⋯	q _2n	$\sum_{j = 1}^{n} ɛ_{j} q_{2 j}$
⋮	⋮	⋮	⋮	⋮	⋮
B _n	q _n1	q _n2	⋯	q _nn	$\sum_{j = 1}^{n} ɛ_{j} q_{nj}$

3.2 BP neural network

The artificial neural network is a processing unit of the neural network which is similar to the human brain, which can simulate the processing of the unit and information knowledge of the human brain. Neural network algorithm can be through the core of the application. It finds the rule of law from a large number of data and it has the characteristics of self adaptation and self-organization. Graph of BP neuron model function is shown in Fig. 1, neural network topology diagram is shown in Fig. 2.

Fig. 1

Graph of BP neuron model function.

Fig. 2

Neural network topology diagram.

The establishment of model

In the above picture, BP neural network model is completed through a series of processes from input signal to the output signal. The process consists of a link to each process node, a function of the unit, and a nonlinear activation function. Among them, the nonlinear activation function is based on the limited value, and there is a threshold value.

The relationship equations between input data and output data are: $β = \sum_{m = 1}^{n} α_{mn} x_{n}$ (6) $y = f (β_{j} - λ_{j})$ (7)

In the above equations, β represents function relation of input signal data. α represents weighted values of connecting neurons and each input signal source. Xm represents a large number of input data sources. ym represents function relation of output signal data. f represents the relationship between the input signal data source and the output signal data source. β_i represents the output signal source that is got by input signal data source through function relation. λ is a threshold which is set in BP artificial neural network. The value is able to activate the input signal data source that exceeds the threshold value and controls the data source to make the function to be further changed and to activate this relationship. The threshold is $f (x) = {\begin{matrix} 1 x \geq 0 \\ 0 x < 0 \end{matrix}$ (8)

Operation algorithm

In the above picture, the input layer, the hidden layer and the output layer are respectively from bottom to top. Connection weights are connected between each level.

Normal transmission process

In the input layer, the output data source of the hidden layer is: $y = f (\sum_{m = 0}^{n} α_{mn} x_{mn})$ (9)

In the above equation, variable data in the input layer is x, output variable data is y, m is the serial number of the input layer node, n is Serial number of implicit hierarchy data node. When the value of x is –1, the data source of the input layer is the data source of the output layer. In other words, the threshold is introduced in implicit level.

In the process of the input layer, the output data source of the output layer is: $v = \sum_{m = 0}^{n} t_{mj} y_{m}$ (10) $L = f (v_{j}) = f (\sum_{m = 0}^{n} t_{mn} y_{m})$ (11)

In the above equation, v is the weight value of connecting the hidden layer and the output layer. When the value of y is –1, the threshold is introduced in output level.

Error correction transfer process

Calculation error of each layer $E = x_{m}^{j} (1 - x_{m}^{j}) (x_{m}^{j} - y_{m}^{j})$ (12)

The number of layers is the same as the number of verifications.

If they are different, the calculation error exists in each layer. $E = x_{m}^{n} (1 - x_{m}^{n}) (x_{m}^{n} - y_{m}^{n})$ (13)

In the process of signal transmission and normal propagation, there will be a certain degree error. The error is expressed by error signal. $e = \frac{1}{2} \sum_{j = 1}^{n} {(r_{j} - L_{k})}^{2}$ (14)

Error signal to the hidden layer is expressed by the following equation. $e = \frac{1}{2} \sum_{j = 1}^{n} {[r_{j} - f (\sum_{m}^{n} t_{m j} t_{m})]}^{2}$ (15)

Error signal to the output layer is expressed by the following equation. $e = \frac{1}{2} \sum_{j = 1}^{n} {(r_{j} - f [\sum_{m = 0}^{n} t_{mj} f (\sum_{m}^{n} α_{mj} x_{m})])}^{2}$ (16)

In the above equation, e is the function relation of the weight value that connects each layer.

The computer operation neural network workflow is as follows.

3.3 Error revision

Overall revision. The above requirements cannot meet the above requirements, so the calculation is repeated. In the process of repeated calculation, the threshold is adjusted. The adjustment formula is as follows. $\partial_{ij} (v + 1) = \partial_{ij} (v) - Δ e_{i}^{k} x_{j}^{k - 1}$ (17)

Partial revision. Taking into account the existence of the BP neural network, the convergence rate is slow and prone to local errors and other issues, momentum factor is increased, partial problem is adjusted (Seifollahi, 2012). The problem can be solved by the traingda, traingdm function in the MATLAB software.

The formula for solving the local problem is as follows. $Δ x (v + 1) = ɛ Δ x (v) + γ (1 - ɛ) \frac{\partial e (v)}{\partial x (v)}$ (18) $x (v + 1) = x (v) + Δ x (v + 1)$ (19)

In the above equation, v is the number of iterations in the computer calculation, γ represents values between 0 and 1, γ is momentum factor between 0–1, in this paper, the value of γ is 0.95.

To solve the convergence problem, the adjustment formula is as follows. $γ (v + 1) = {\begin{matrix} 1 γ (v), e (v + 1) < e (v) \\ 0.5 γ (v), e (v + 1) > 1 e (v) \\ γ (v), others \end{matrix}$ (20)

Weight revision. In order to overcome the serious deficiencies of the grey model and multiple regression, by the propagation of the learning algorithm in the opposite direction, the weights are adjusted as follows. $γ_{mn} = γ_{lk} - α \frac{\partial e}{\partial γ}$ (21)

There is the following equation. $\frac{\partial e}{\partial v_{mn}} = \sum_{j = 1}^{m} \frac{\partial e}{\partial v_{mn}}$ (22)

The correlation coefficient is determined. $X^{2} = \frac{\sum_{i = 1} (x_{i} - \bar{x_{i}}) (\overset{\land}{x_{i} - \overset{\bar{\land}}{x_{i}}})}{\sqrt{\sum_{i = 1} {(x_{i} - \bar{x_{i}})}^{2} {(\overset{\land}{x_{i} - \overset{\bar{\land}}{x_{i}}})}^{2}}}$ (23)

Among them, there are the following equations. $\bar{x_{i}} = \frac{1}{n} \sum_{i = 1}^{n} x_{i}$ (24) $\bar{\overset{\land}{x_{i}}} = \frac{1}{n} \sum_{i = 1}^{n} \overset{\land}{x_{i}}$ (25)

4 Education with the technology

4.1 Cloud computing and education

Cloud computing service platform for the construction of the teaching environment provides technical feasibility and security, teachers and students use the platform to customize the teaching situation and collaborative learning. For the cloud computing and education framework as shown in Figs. 3 and 4, it should be organized as follows.

Fig. 3

The computer running flow chart of neural network to work.

Fig. 4

Cloud computing and education framework.

The core application layer plays a key role in the construction of cloud computing network teaching platform, which is the core of the whole system platform. It fully embodies the planning, management, implementation and evaluation of teaching, which is the complete embodiment of education management. Adding network labs, teaching resources, search engine and other functions on the existing basis, it has improved system setting of the core application layer. Through the application layer platform, users can continuously improve the database, software library and other functions.

The basic architecture of the cloud platform includes operation management ability basic framework ability, deployment ability and development test ability. Parallel computing is to take into account the decomposition of the task itself while taking into account the use of parallel models and network connectivity and other factors.

The cloud platform operation management level mostly develops by the third-party software supplier that manages the platform through the operation to realize the functions and the resources unification management, system monitoring, backup management. The user may carry on the independent development to the operation management level, according to own demand with the perfect operation management level platform.

It is beneficial to the resource mobilization and allocation. The virtualization technology can hide the complex programs, and for the user, there is no need to know the specific location of the server, network, etc. Resources can be abstracted and easy to use through the virtualization layer. When the system fails, it can be diagnosed and repaired.

With “cloud computing”, students can tailor their learning plans to their own needs and no longer need to focus on the same content. Learners do not need to understand advanced computer technology and use the complex software, so long as they can use web browser, they can enjoy rich online learning resources anytime and anywhere. In the teaching classes of the cloud services, teaching content can be obtained from the cloud. The teaching process of teachers and the learning process of the students have significant interaction characteristics. Throughout the teaching process, students are in the state of “man-machine conversation” with computers and networks. Using this concept, we use the various systems related to teaching in colleges and universities to construct a multimedia teaching environment cloud service platform that also meets the requirements of a constructivist learning environment and provides one-stop teaching services to assist teachers in teaching and promote collaborative learning.

Decision theory based on the mathematical countermeasure theory, from the initial development to the plastic model, until the modern “bounded rationality” decision theory, it has become a social development in dealing with important theoretical weapon of various kinds of complicated conditions. Cloud computing technology can integrate the scattered vocational teaching resources, so as to realize the sharing of education and teaching resources and promote and develop the awareness of resource cooperation among the various social institutions. Cloud technology provides a shared pool, each institution can upload its own teaching resources in a shared pool after the sharing mechanism is reached, thus forming a content sharing platform. Online learning platform as shown in Figs. 5 and 6.

Fig. 5

Multimedia system architecture and the potential applications on education.

Fig. 6

Online learning platform.

Therefore, the method can be separated into the following scenarios. (1) Teaching and learning aspects of the application. Currently, cloud computing used in teaching practice is collectively referred to as the “education cloud.” Educational cloud can then effectively avoid the shortcomings of the traditional information teaching. For example, it effectively reduces the waste of the teaching resources and eliminates the need for repeated investment in a large number of hardware infrastructures in schools. The problems of improving network security, teaching data in the cloud, data loss and virus infringement can be solved. Between colleges and schools and the teaching resources can be shared. (2) Experimental applications. Cloud computing applications in the experimental teaching is the main principle of: a thin client via the keyboard and mouse operations such as triggers a desktop application service program or the operating system, to realize the recycling of the resources required in the center of the cloud data, application, regulation, and powerful computing capacity computing resources pool. (3) Application of classroom teaching. In the actual teaching process, it is often due to the limitations of geographical conditions, resulting in the distribution of educational resources uneven distribution. Traditional education mode investment is huge, and efficiency is not high. The “cloud” platform can realize the sharing of high-quality teaching resources and the promotion of new teaching methods through the network remote access, so as to integrate the infrastructure and achieve centralized management.

4.2 The multimedia based education

Teaching courseware is a core component of multimedia teaching, so the quality of multimedia courseware directly affects the effect of classroom teaching. There are many ways to make multimedia courseware, the tools and software used are also varied, and the organization of the content varies from person to person, multimedia teaching in our country after about ten years of application exploration and discussion, its advantages mainly in the following aspects. (1) As a comprehensive utilization of a variety of media, students can give more sense of stimulation, in line with the study of physiological and psychological laws is conducive to students’ understanding and mastery of knowledge. (2) The multimedia teaching makes the teacher liberate from the heavy blackboard writing, is more advantageous to the teacher language, the personality charm play that enhances the classroom teaching time the utilization rate and the teaching quality. (3) Multimedia teaching is usually the combination of image and image. The image is intuitive and vivid, which can stimulate students’ interest in learning and the desire for knowledge. (4) Multimedia teaching can highlight the key points and difficulties of teaching through convenient and retrospective teaching and make the teaching process more repeatable and profound.

The reappearance and simulation of the real situation through multimedia can be then extended to the general understanding experiment, which is conducive to the cultivation of general students’ exploration ability and creative ability. Large amount of information, large capacity, save space and time will improve teaching efficiency. Although multimedia teaching is an effective and advanced teaching mode, it cannot replace the dominant position of teachers. In teaching, teachers’ charisma and interest-based explanations are used to motivate students to actively participate in teaching through teacher-student emotions, which cannot be replaced by any form of the electronic media. With the use of multimedia teaching, we can then increase the classroom knowledge capacity to ease the current teaching content and smooth the hours of contradictions, but students should pay attention to the rhythm. Teaching should go out of “misunderstanding” that “the more we talk, the more students learn; the more we talk about the students, the more comprehensive the students learn”, and the teaching principle of “less but better” and “heuristic”. In teaching activities, students are the main body, teachers play a leading role, and multimedia is an auxiliary means for the purpose of teaching. However, in actual teaching, some teachers blindly use the multimedia means to reproduce all the teaching links in spite of the actual teaching needs, resulting in the overflow of invalid information in the classroom. Therefore, for successfully apply the usage of the multimedia-based teaching regulation we shall follow the listed suggestions. MATLAB operation results as shown in Fig. 7.

Fig. 7

Analysis of MATLAB operation results.

5 Case analysis

5.1 The determining of weights

There are many factors that affect college students’ English culture experiential teaching, including the professional academic, individual learning ability and cognitive consciousness, and so on [9]. Adhering to the principles of comprehensiveness, emphasis, hierarchy, pertinence and feasibility, taking into account the index level and political ideology, political performance, moral accomplishment and behaviors related moral quality, learning attitude, learning achievement, professional skills, scientific and technological innovation and the professional quality of scientific research achievements, physical fitness, sports ability, activity related to style quality, the index system of college students’ English culture is established. Judgment matrix as shown in Tables 4 –8.

Table 4
A-BJudgment matrix

A-B B1 B2 B3 WEIGHT

B1 1 1/5 3 0.2634

B2 5 1 5 0.5989

B3 1/3 1/5 1 0.1653

A-B	B1	B2	B3	WEIGHT
B1	1	1/5	3	0.2634
B2	5	1	5	0.5989
B3	1/3	1/5	1	0.1653

Table 5

B1-CJudgment matrix

A-B	C11	C12	C13	C14	WEIGHT
C11	1	1/3	1	1	0.2346
C12	3	1	3	3	0.3689
C13	1	1/3	1	1/3	0.1453
C14	1	1/3	3	1	0.2341

Table 6

B2-CJudgment matrix

A-B	C21	C22	C23	C24	C25	WEIGHT
C21	1	1/7	1/5	1/5	1/9	0.05978
C22	7	1	3	3	1/3	0.2653
C23	5	1/3	1	1	1/3	0.1542
C24	5	1/3	1	1	1/3	0.1325
C25	9	3	3	3	1	0.3999

Table 7

B3-CJudgment matrix

A-B	C31	C32	C33	WEIGHT
C31	1	1/3	1/2	0.1657
C32	3	1	1	0.4432
C33	2	1	1	0.3654

Table 8

A-B-C Judgment matrix

A-B	C31
C11	0.0546
C12	0.0978
C13	0.0380
C14	0.5467
C21	0.0345
C22	0.1546
C23	0.0989
C24	0.0989
C25	0.2145
C31	0.0234
C32	0.0674
C33	0.0601

5.2 Judgment matrix

By MATLAB software, the comparison result of the judgment matrix is tested by the consistency test. The maximum eigenvalue of the matrix is obtained through the consistency check. The judgment matrix is as follows:

Through the operation of MATLAB software, the results are obtained. $λ = 3.6422, CI = 0.0325, CR = 0.0536 < 0.01$

Through the operation of MATLAB software, the results are obtained. $λ = 45422, CI = 0.0236, CR = 0.0287 < 0.01$

Through the operation of MATLAB software, the results are obtained. $λ = 5.6784 CI = 0.0125 CR = 0.0115 < 0.01$

Through the operation of MATLAB software, the results are obtained. $λ = 5.5263, CI = 0.0153, CR = 0.0121 < 0.01$

5.3 Comprehensive evaluation

Normalized evaluation index scores have been evaluated as input signal data sources. Comprehensive evaluation weight, which is obtained by AHP, is regarded as output vector. Bycontinuously calculating the weight of the score matrix and the weight of the algorithm in the neural network, an effective evaluation of the network is built. Then the real values of the neural network are took into the exercise process. The obtained results are compared with the expected results. If the results are meet the conditions, they will be retained. If not, the results will be dropped.

5.4 Normalization processing

The original data are normalized as follows: $PN = (P - MIN) / - MAX - MIN$ (26)

In the above equation, P is input value of College English Teaching. PN is input value of evolution. MIN is minimum input values of college experiential English. MAN is maximum input value of college Experience English.

The neural network model which is studied in this paper is three-layer structure. Because there are 12 output sources, 12 input sources are added. According to AHP, $W = \sqrt{I + O} + E / - 2$ (27)

In the above equation, E is the number of neural network testing. W is layer number of hidden layers. I is layer number of input layer. O is Layer number of output layer. Through calculation, W = 15.

The 12 indicators are normalized.

5.5 MATLAB operation result and analysis

By testing the model, $c = \frac{\sqrt{\frac{\sum (y_{i} - \bar{y)^{2}}}{n - 1}}}{\sqrt{\frac{\sum ([Δ_{i} - \bar{Δ})^{2}}{n - 1}}}$ (28)

The above equation is variance ratio of application.

The Error value is got. $P = P ((Δ_{i} - \bar{Δ})) ≺ μ \sqrt{\frac{\sum ([Δ_{i} - \bar{Δ})^{2}}{n - 1}}$ (29)

According to the above equation, the accuracy is got by using computer, and then it will be compared.

By the MATLAB software, the results between the real data value and the analytic hierarchy process are as follows:

In the above picture, TRUE is real data source, EXPECT is expected data, ERROR is error between real data and expected data. From the picture, the real value and the expected value are almost coincident, error values are in (–1,+1), the error is less. It can be seen that the influence factor of the computer software on college English culture experiential teaching is similar to the result of the numerical analysis method and the result of AHP. The accuracy is high. Therefore, the computer software can accurately evaluate the college English teaching.

6 Conclusions

In the background of the current rapid development of the information age, it is very important to use computer to realize the application of work and life. On the problem of computer in the evaluation system, in this paper, the evaluation of college English culture teaching that is obtained by the analytic hierarchy process is regarded as the expected result. The error value is in the range of –1 to 1; in other words, the error is small. Obviously, computer software can realize the evaluation of experiential teaching of college English culture. This method is also applicable to other evaluation with the use of computer software. This paper discusses the multimedia assisted English teaching model based on computer platform. Knowledge construction refers to the knowledge transfer system, the main object of possession or acceptance of knowledge, which includes knowledge, knowledge consolidation and knowledge application of three links. In multimedia teaching process, the main body of the predecessors’ through a series of cognitive activities into their cognitive, builds up in your mind and the page or screen in the form of the teaching material structure of the corresponding knowledge structure, to identify the corresponding things and to solve the problem.

References

Angappa

, Research and Applications in e-commerce and third-party logistics management, International Journal of Production Economies5(113) (2008), 123–126.

Benardos

, Vosniakos

, Optimizing feedforward artificial neural network architecture, Engineering Application of Artificial Intelligence20(3) (2007), 365–382.

Gao

, Wu

, An optimization method for the topological structures of feed- forward multi-layer neural networks, Pattern Recognition31(9) (1998), 1337–1342.

González

, González

, The co-creation as a strategy to address IT governance in an organization,rica de Sistemas e Tecnologias de Informação, RISTI-RevistaIb’e (14) (2015), 1–15.

John

, Tomas

, Mult logistics service quality as a segment-customized process, Journal of Marketing65 (2001), 82–104.

Jacxsens

, Liming

, Tools for the performance assessment and improvement of food safety management systems, Trends in Food Science & Technology14(22) (2011), 10–11.

Lin

, Jou

, GA-based reinforcement learning for neural networks, International Journal of Systems Science29(3) (1998), 233–247.

Lier

L.V.

, The Ecology and Semiotics of Language Learning– A Sociocultural Perspective. Kluwer Academic Publishers, 2004, 10–14.

Muller

, Mika

, An introduction to kernel-based learning algorithms, IEEE Trans. on Neural Networks2 (2001), 181–201.

10.

Zhenhua

Huang

, Guangxu

Shan

, Jiujun

Cheng

and Jian

Sun

, TRec: An Efficient Recommendation System for Hunting Passengers with Deep Neural Networks, Neural Computing and Applications, (2018).

11.

Azizi

, Rezakazemi

, Zarei

M.M.

, An intelligent approach to predict gas compressibility factor using neural network model. Neural Computing and Applications, 2017, pp. 1–10.

12.

Demertzis

, Iliadis

, Avramidis

, El-Kassaby

Y.A.

, Machine learning use in predicting interior spruce wood density utilizing progeny test information, Neural Computing and Applications28(3) (2017), 505–519.

13.

Ding

, Zhang

, Wu

, Twin support vector machine: theory, algorithm and applications, Neural Computing and Applications28(11) (2017), 3119–3130.

14.

Finardi

K.R.

, Silveira

, Lima

, Mendes

A.R.

, MOOC in the Inverted CLIL Approach: Hybridizing English Teaching/Learning. Studies in English Language Teaching, 4(4) (2016), 473.

15.

, The Strategy of Integrating Enterprise Culture into College English Teaching Under the New Curriculum Reform. DEStech Transactions on Social Science, Education and Human Science, (asshm), 2016.

16.

Liu

, Global exponential convergence of non-autonomous SICNNs with multi-proportional delays, Neural Computing and Applications28(8) (2017), 1927–1931.

17.

, He

, Exploration on English Task-based Learning Teaching Mode– -from a Perspective of New Curriculum Reform. DEStech Transactions on Social Science, Education and Human Science, (isetem), 2016.

18.

Oshaba

A.S.

, Ali

E.S.

, Elazim

S.A.

, PI controller design using ABC algorithm for MPPT of PV system supplying DC motor pump load, Neural Computing and Applications28(2) (2017), 353–64.

19.

Phan

N.T.T.

, Phan

N.T.T.

, Locke

, Vietnamese teachers’ self-efficacy in teaching English as a Foreign Language: Does culture matter?, English Teaching: Practice & Critique15(1)(2016), 105–128.

20.

Chen

, Pattabiraman

, Lasseter

R.H.

and Jahns

T.M.

, CERTS microgrids with photovoltaic microsources and feeder flow control. In Energy Conversion Congress and Exposition (ECCE), 2016 September, IEEE (pp. 1–8). IEEE.

21.

Knoblauch

, Tepler Drobnitch

, Peters

W.S.

and Knoblauch

, In situ microscopy reveals reversible cell wall swelling in kelp sieve tubes: one mechanism for turgor generation and flow control?, Plant, cell & environment39(8) (2016), 1727–1736.

22.

Liu

, Jiao

, Chen

, Writing Collaboratively Via WIKI: An English Teaching Study. In International Conference on Blending Learning. Springer International Publishing, 2016, July, pp. 14–23.

23.

Gao

, Analytic Hierarchy Process Evaluation of English Teaching Quality in Application-Oriented Universities,Systems, Science & Technology, International Journal of Simulation – Systems, Science & Technology17(39) (2016).

24.

Dong

, Shi

, Lou

, Ding

, Application and evaluation research on group decision-making model in English teaching. In SHS Web of Conferences. EDP Sciences, Vol. 25, 2016, January.

25.

Sarioglu

, Control of flow around a square cylinder at incidence by using a splitter plate, Flow Measurement and Instrumentation53 (2017), 221–229.

26.

Wang

, Ren

, Zhong

Q.C.

, Robust power flow control of grid-connected inverters, IEEE Transactions on Industrial Electronics63(11) (2016), 6887–6897.

27.

B. A

, Experiencing Different Identity Prototypes in Learning and Teaching English: A Chinese Learner’s Autoethnography, Changing English23(3) (2016), 280–291.