[目的 /意义]针对目前融合情境因素的信息推荐方法大都存在推荐前的情境过滤(pre-filtering)和推荐后的情境过滤(post-filtering)所导致的价值信息流失问题,将情境因素融入到推荐过程中,实现基于用户-资源-情境的多维推荐。[方法 /过程]将情境因素融入推荐的过程中,动态挖掘在不同情境下用户兴趣的偏好,利用社会网络的相关指标赋予用户兴趣初始值,从空间距离的视角计算用户兴趣的权重,最后,借鉴内容过滤和协同推荐的思想实现用户的评分预测,进而按照用户的兴趣进行推荐。[结果 /结论]与以往二维推荐的实验比较表明,将情境因素融入到推荐过程中的方法在减少价值流失的基础上,能更为准确地揭示用户的兴趣,提高推荐质量,为存在社会关系的社会化媒体推荐服务提供借鉴。 [Purpose / Significance] Most of the current information recommendation methods based on contextual factors include the loss of value information caused by pre-filtering before pre-filtering and post-filtering after recommendation, and integrating situational factors into During the recommendation process, a multi-dimensional recommendation based on user-resource-context is implemented. [Method / Process] Contextual factors are incorporated into the recommendation process to dynamically mine user preferences in different contexts, to use social network indicators to give initial values ​​of user interest, and to calculate user interest weights from spatial perspectives. Finally, Reference content filtering and collaborative recommendation ideas to achieve the user’s score forecast, and then in accordance with the user’s interest to recommend. [Results / Conclusions] Compared with the previous two-dimensional recommended experiments, the method of integrating situational factors into the recommendation process can reveal the user’s interest more accurately and improve the quality of recommendation on the basis of reducing the loss of value, Relationship social media recommendation service to provide reference.