基于知识关联度的电力大数据协同过滤推荐算法

The collaborative filtering recommendation algorithm of power big data based on knowledge correlation

针对电力大数据推荐结果排名没有考虑电网领域知识关联度,推荐结果的准确度不高的问题,提出了引入知识项关联度的协同过滤推荐算法AR-Item CF.通过计算用户推荐列表得到最终推荐结果.结果表明,该算法能有效地解决推荐结果关联度较低的问题,显著地提高了推荐结果的质量和推荐效率.

Most collaborative filtering recommendation algorithms are based on the object similarity without taking knowledge correlation in grid domain into account,which leads to inaccurate ranking result.Aiming at this problem,this paper adopts the structure of knowledge tree to organize grid domain knowledge and mines the correlation between different knowledge items.The experiment results show that the algorithm can effectively solve the problems of the low correlation degree of recommendation results and significantly improve the quality of the recommendation results and the recommendation efficiency.