电子商务智能推荐系统中基于领域本体的案例检索算法

Case retrieval algorithm based on domain ontology in intelligent recommendation system of e-commerce

针对传统电子商务推荐算法的不足,提出了综合语义相似度的案例检索算法。算法通过加权平均商品的概念语义相似度、基于类型的属性语义相似度和基于数据类型的属性值相似度,来计算案例的综合相似度,避免了传统推荐算法中计算相似度仅靠属性值,没考虑语义和属性类型的影响造成的效率低、精度差等问题。设计了领域本体协同案例推理的电子商务智能推荐系统架构,通过在领域本体中抽取语义要素对案例进行表示,拓宽了案例求解空间,达到了协助用户检索及完成商品推荐的任务。经实例对比分析该算法有效且精度较高。

In view of the shortcomings of the traditional e-commerce recommendation algorithm,the case retrieval algorithm of synthetic semantic similarity was developed in this paper.Through the concept semantic similarity of weighted average commodity,type-based attribute semantic similarity and data-based type attribute value similarity,the comprehensive similarity of the case was calculated.The proposed algorithm solved the problem of low efficiency and inferior precision that calculating the similarity only depended on the attribute value and did not consider semantic and attribute type influence in the traditional recommendation algorithm.The e-commerce intelligence recommendation system framework was designed based on domain ontology cooperated with case reasoning.Through extracting the semantic essential factor in the commercial domain ontology to express the case,the case solution space was opened up to assist user retrieval and complete the commodity recommendation.The experimental results prove that this algorithm is effective and accurate.