%0 Journal Article
%T 融合效用与兴趣的在线用户健康干预推荐<br>Fusing Utility and Interest: Recommendation of Healthcare Interventions for Online Users
%A 严晗
%A 尹裴
%A 张骏
%A 宋俊杰
%J Modeling and Simulation
%P 3181-3195
%@ 2324-870X
%D 2024
%I Hans Publishing
%R 10.12677/mos.2024.133291
%X 面向在线健康社区的推荐，系统需要推荐用户感兴趣且能改善其健康状况的干预方案。为此，本文提出了融合效用与兴趣的在线用户健康干预推荐模型，先利用注意力机制对用户兴趣进行学习，同时计算待推荐方案对其参与者的预计疗效，接着评估干预方案对目标用户的效用，最终结合方案效用和用户兴趣得出推荐结果。实验结果证明与其他推荐模型相比，本文模型有最好的推荐结果且能提高推荐的方案对于用户的效用。<br />
The recommendation systems tailored for online health communities necessitate suggesting interventions that align with users’ interests while also enhancing their health outcomes. In this regard, this paper proposes an integrated online health intervention recommendation model, which amalgamates utility and interest considerations. Initially, an attention mechanism is employed to discern user interests, concurrently computing the anticipated therapeutic effects of candidate interventions for their participants. Subsequently, the utility of intervention plans for target users is evaluated, culminating in the fusion of scheme utility and user interest to derive recommendation outcomes. Experimental findings corroborate that compared to alternative recommendation models, the proposed model yields superior recommendation results and enhances the utility of recommended schemes for users.
%K 推荐系统，在线健康社区，效用，深度学习，注意力机制<br>Recommendation Systems
%K Online Health Communities
%K Utility
%K Deep Learning
%K Attention Mechanism
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=87943