| 摘 要： | 我国智慧城市安全概念的普及和建设的逐渐落地,以及大数据在智慧城市安全建设方面的深度应用,对关键词检索的处理响应速度提出了更高的要求。针对这一问题,提出了基于城市安全知识图谱的流式知识图谱多关键词并行检索算法(MKPRAS...展开更多
我国智慧城市安全概念的普及和建设的逐渐落地,以及大数据在智慧城市安全建设方面的深度应用,对关键词检索的处理响应速度提出了更高的要求。针对这一问题,提出了基于城市安全知识图谱的流式知识图谱多关键词并行检索算法(MKPRASKG),该算法能够根据用户输入的查询关键字,通过关联类图的构建、剪枝和融合操作实时构建基于知识图谱实体的查询子图集,再结合评分函数,以高评分的查询子图为指引,在知识图谱实例数据中进行并行搜索,最终返回Top-k查询结果。实验结果证明,该算法在实时搜索、响应时间、搜索效果以及可扩展性等方面均具有较大的优势。收起
With the popularization and construction of the concept of smart city security in China,and the deep application of big data in the construction of smart city security,higher requirements on the processing response speed of keyword retrieval are needed.Aiming at this pr...MORE
With the popularization and construction of the concept of smart city security in China,and the deep application of big data in the construction of smart city security,higher requirements on the processing response speed of keyword retrieval are needed.Aiming at this problem,this paper proposed a streaming multi-keyword parallel retrieval algorithm based on the urban security knowledge graph(MKPRASKG).This algorithm can construct a query subgraph set based on the entities of knowledge graph through the construction,pruning and fusion operation of the associated class graphs based on the query keywords input by the user in real time.And then combined with the scoring function,the high-scoring query subgraph is used as a guide,and the parallel search is performed in the knowledge graph instance data,and finally the Top-k query results are returned.Experimental results show that this algorithm has great advantages in terms of real-time search,response time,search effect and scalability.FEWER
|
