关键词: 单条件三元概念, 启发式方法, 项目条件权重, 项目流行度, 融合推荐置信度

Abstract:
Abstract: Triadic concept analysis has been introduced into the field of recommendation systems. However， the fusion step of concepts increases the complexity of constructing triadic concepts， and the concept information is not fully utilized in recommendation. This paper directly uses single-condition triadic concepts for recommendation， and designs a construction method and fusion recommendation algorithm for single-condition triadic concepts. Firstly， the triadic context is decomposed into multiple single-condition triadic contexts， and the concept proportion is designed as heuristic information to generate single-condition triadic concept. Then， the popularity of the recommended items on the single-condition triadic concepts is calculated， and the fusion recommendation confidence is designed by combining the item condition weight of the triadic context. Finally， the target user is recommended by combining the fusion recommendation confidence and the recommendation threshold. This paper conducts experiments on six public datasets. The results show that on datasets with low sparsity， the algorithm proposed in this paper is slightly better than the recommendation effects of GRHC and GreConD-kNN， and comparable to the effects of IBCF and kNN.

Key words: single-condition triadic concept, heuristic method； item condition weight； item popularity； fusion recommendation confidence