Sharing Model of Online Overseas Chinese Education Resource Based on Cloud Computing

In recent years, with the sustainable and fast development of chinese economy, there has been increasing interest in overseas chinese language. As an important way of overseas chinese education, online education has been drawing more and more attention due to its simplicity and convenience. But at present, the existing chinese education resource service model is simply assigned the resources to users which can not effectively meet the practical needs of users. How to provide a personalized service is the key problem to be solved. In this paper, we proposed a sharing model of chinese education resource based on cloud computing. There are three mainly works in this paper. Firstly, user vector space is constructed based on user personal information. Secondly, synergetic neural network is presented to user group recognition. Finally, sharing model based cloud computing is presented and implemented. The proposed model in this paper provide a good practicability and a promising future for overseas chinese education.


I. INTRODUCTION
With the great development of Chinese economy, the influence of Chinese education becomes more and more larger.At present, many countries and regions have established Confucius institute and Confucius classroom.Overseas chinese education [1,2] has made tremendous contributions.However, due to historical reasons and international environment, the overseas Chinese teaching resources are relatively scattered and weak, which will great influence the development of overseas Chinese education.How to better share the Chinese overseas resources and provide personalized service is the key problem urgently to be solved at present.
In recent years, with the development and popularity of network, information services everywhere.At the same time, there have been some problems such as rising demand, massive data growth, and heterogeneous distribution of resources.Cloud computing [3,4] as a new shared infrastructure approach can enable large amounts of data and processor resources to work together, so as to provide users with a variety of storage and computing resources.Cloud computing can combine the database into a onestop search interface together.
At present, the existing Chinese education resource is statically assigned to users which can not meet the needs of users.User modeling method [5][6][7] should be automatically constructed according to the user's browsing content and browsing behavior.A key problem of intelligence user server model is how to classifier and indentify the user groups.It can offer better service only when the user groups can be effectively identified.
Synergetics [8][9][10] is the science proposed by Haken to explain the phase transition and self-organization in nonequilibrium system.In the late 1980s, Haken proposed to put synergetic theory into a new field: synergetic information processing, which includes synergetic neural network, synergetic information theory and synergetic computer, etc [11][12][13] .
In this paper, we presents a sharing model of Chinese education resource based on cloud computing.This paper is organized as follows.Firstly, the oval sharing model is presented.Secondly, some key algorithm of our proposed model is implemented.Finally some discuss and conclusions are given on the model.

II. THE RESOURCE SHARING BASED ON CLOUD COMPUTING
In this section, we present a personalized service model based on cloud computing.Firstly, we can build user information vector based on the characteristics of users.Secondly, we proposed a user group classification algorithm based on synergetic neural network .Finally, A personalized information sharing model based on the cloud computing is presented.The sharing model is shown in figure 2.

A.
User information vector The user information can be viewed as a vector, so we can better describe the relationship between user groups.The user information space is show as follow.User group classification In synergetics, high dimension and nonlinear problem can be described as a set of low-dimension nonlinear equations, which focuses on the research of the qualitative change of macro-feature in complex system.The basic principle of synergetic neural network is that the pattern recognition procedure can be viewed as the competition progress of many order parameters.The strongest order parameter will win by competition and desired pattern will be recognized.User identification is a classification problem, we use synergetic neural network to realize the user classification.Cloud service model The cloud service model consist cloud monitor, user groups and server pool.Cloud monitor is responsible for managing user groups and server pool.Nodes in server pool are responsible for providing servers.When computers online apply for joining the system, monitor adds it to the server pool.If one node is in error, monitor deletes it from the server pool.Monitor adds user group to user group's pool.And all the results are summarized and exported to users.

III. THE IMPLEMENTED OF OUR PROPOSED MODEL
A.
The comstruction of user vector space and similarity measure TF-IDF (term frequency-inverse document frequency) [14,15]is a commonly used weighting technique for information retrieval and text mining.TF-IDF [5,6] is a statistical method used to assess the degree of importance of a word for one of the documents in a set of files or a corpus.The process of constructing the TF-IDF vector is described below.
Supposed the weight vector for document d is

B. Synergetic neural network (SNN ) model
An unrecognized pattern, q , is constructed by a dy- namic process which translates q into one of prototype pattern vectors k v through status ( ) q t , namely, this pro- totype pattern is closest to (0) q .The process is described as following equation: Dynamic equation can be given for a unrecognized patter Corresponding dynamic equation of order parameters is: Where k !satisfies initial condition: (0) . A method for label semantic roles using Synergetic neural network technique is given as Figure 3.
Order parameter reflects the similarity between user groups,the order parameters of j d and query q can be calculated as:  The overall implementation process can be expressed as Algorithm 1.

1) TF-IDF algorithm is used to construct user vector space
2) Calculate the order parameter based on according to the above formula ( 2  2) Synergistic neural network used to user group classification can quickly determine user groups.

Figure 2 .
Figure 2. Sharing mode based on cloud computing

Figure 3 .
Figure 3.The users model based on synergetic neural network

Figure 4 .
Figure 4.The realization of cloud computing model

) 3 ) 4 )Algorithm 1 .
Set the attention parameters , B C and non-atten- tion parameter k ! ; We can obtain the best group through the evaluof order parameter equation according to the above formula (1).5) Cloud service model is constructed and implemented.6) Resource sharing based on personal information.Overseas Chinese education resource Sharing based on cloud computing IV.CONCLUSIONS In this paper, we present a sharing model of Chinese education resource based on cloud computing.This is the first effort to introduce cloud computing and SNN model to Chinese education resource Sharing.The proposed model provides a good practicability and a promising future for Chinese education resource sharing.We got the following conclusions.

1 )
The model based on cloud computing can effectively achieve the purpose of resource sharing Chinese education.