Title: Semantic retrieval method for online and offline collaborative education and teaching resources based on Bayesian networks

Authors: Yanling Xu

Addresses: Department of Culture and Arts, Yongcheng Vocational College, Yongcheng, Henan, China

Abstract: In order to solve the problems of high omission rate and poor consistency of retrieval results in semantic retrieval of teaching resources, this paper designs a semantic retrieval method of online and offline collaborative education and teaching resources based on Bayesian network. Firstly, the doc2vec model is used to characterise the semantic characteristics of resources. Secondly, the similarity between semantic features and index vectors is calculated to extract semantic features. Then, by assigning weights to semantic feature vectors through IDF values, a keyword balanced binary tree is constructed to sort semantic feature vectors. Finally, the Bayesian network retrieval model is constructed and the retrieval results are output. The results show that the missing detection rate is less than 1%, the retrieval consistency is higher than 0.9, and the highest false detection rate is only 0.12%, indicating that the retrieval effect of the proposed method has certain advantages.

Keywords: Bayesian network; teaching resources; semantic retrieval; Doc2Vec model; IDF value; balanced binary tree.

DOI: 10.1504/IJCAT.2024.146140

International Journal of Computer Applications in Technology, 2024 Vol.75 No.2/3/4, pp.146 - 155

Received: 17 Jul 2024
Accepted: 02 Jan 2025
Published online: 07 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article