Research On Personal Network Teaching Based On Tata Mining

Distance education has become the new growth point of education development and primary developing trend of modern education technology. There are many problems in current distance education, such as singularity teaching mode, educational resource stacking simply, low intelligentized level etc. But different student has different learning capability, personal interest, personal learning foundation and struggling level. Contradiction grows up between distance education and personal demand of student.Based on national distance education standard (CELTS) and Web data mining, this paper mainly deals with using personalization service in distance education. Its main work includes:1. Analysis distance education standard around the world. The learner standard and resource standard, which are correlated with personal network teaching, has been studied.2. The research on Web data mining, which is the key technology for designing personal network teaching, is carried out.3. Analysis the disadvantage of current network teaching platform, a personalization service model (PNTM) is established. Based on CELTS, student sub-model defines basic information and interest information of student, collects student interest character with Interest Collection algorithm and distills recommendation resource with Personalization Output algorithm. Education resource sub-model defines basic information and character information for resource. After studying Web data mining, Web access transaction model was present; it defines some important concept, such as Web access frequent itemsets, Web access association rule.4. The research on system structure and principle of PNTM is carried out. Combining with Web data mining technology, this model provide student with personal recommendation service and personal customization service.5. The research on personal recommendation engine, which is the key technology ofPNTM, is carried out. The personalization recommendation algorithm is proposed in personal recommendation engine. This algorithm generates personal recommendation content according with changing of student interest character.6. The directions of research in this area are introduced.