Font Size: a A A

Research And Implementation Of Personalized Knowledge Service System In Community E-learning

Posted on:2007-03-23Degree:MasterType:Thesis
Country:ChinaCandidate:Q LuoFull Text:PDF
GTID:2178360212957051Subject:Circuits and Systems
Abstract/Summary:PDF Full Text Request
The theory and practice of learning community is a hotspot in academic circles, which is paid more attention by the society. Because it is the foundation of constructing learning society, realizing lifelong education, and promoting human society's progress and development effectively.The advanced technology of network, computer and artificial intelligence is applied in the learning community, and a personalized service model based on community E-Learning (PSSCE) is proposed in the paper. The idea of personalized information service, personalized recommendation and personalized retrieval are introduced in community E-Learning, which captures users' personalized accessing characteristics of teaching resources real-timely. Teaching resources are filtered according to users' personalized characteristics.Based on tradition filtering algorithm, an adaptive filtering algorithm based on vector space model is proposed in the paper. First, feature selection and pseudo feedback are used to select the initial filtering profiles and thresholds through training algorithm. Then user feedback is utilized to modify the profiles and thresholds adaptively through filtering algorithm. The algorithm has two advantages, the first is that it could carry on self-study to improve the precision; the second is that the execution do not need massive initial texts in the process of filtering.Integrating the merits of user obvious feedback and user hiding feedback, a new user establishing model algorithm, namely a mix establishing model method based on vector space model is also proposed. On the one hand, user initial interest model is established according to user obvious feedback (user register information). On the other hand, user interest model is updated according to user hiding feedback (observing user's behavior in web server log).After the test use of the system by some certain communities, we find that the system could improve the residents' initiative participation in the community education and training. Thus, we think it may be a practical solution to realize self- learning and self-promotion in the lifelong education age.
Keywords/Search Tags:Learning Community, Personalized Service, E-Learning, Adaptive Filtering, Vector Space Model, Teaching Resources
PDF Full Text Request
Related items