*q*，在HINs中查询包含

*q*的稠密子图，已成为该领域的热点和重点研究问题，并在活动策划、生物分析和商品推荐等领域具有广泛应用.但现有方法主要存在以下两个问题：（1）基于模体团和关系约束查询的稠密子图具有多种类型顶点，导致其不能解决仅关注某种特定类型顶点的场景；（2）基于元路径的方法虽然可查询到某种特定类型顶点的稠密子图，但是它忽略了子图中顶点之间基于元路径的连通度.为此，本文首先在HINs中提出基于元路径的边不相交路径的连通度，即路径连通度；然后，基于路径连通度提出

*k*-路径连通分量（

*k*-PCC）模型，该模型要求子图的路径连通度至少为

*k*；其次，基于

*k*-PCC模型提出最大路径连通Steiner分量（SMPCC）概念，其为包含

*q*的具有最大路径连通度的

*k*-PCC；最后，提出一种高效的基于图分解的

*k*-PCC发现算法，并在此基础上提出优化查询SMPCC算法.大量基于真实和合成HINs数据的实验结果验证了本文所提出模型和算法的有效性和高效性.

*q*, we can find the cohesive subgraphs containing

*q*in HINs, has become an important problem, and has been widely used in various areas such as event planning, biological analysis and product recommendation. Yet existing methods mainly have the two deficiencies:(1) cohesive subgraphs based on relational constraint and motif cliques contain multiple types of vertices, which makes it hard to solve the scenario of focusing on a specific type of vertices. (2) Although the method based on meta-path can query the cohesive subgraphs with a specific type of vertices, it ignores the meta-path-based connectivity between the vertices in the subgraphs. Therefore, we first propose the connectivity with novel edge-disjoint paths based on meta-path in HINs, i.e., path-connectivity. Then, we raise the

*k*-path connected component (

*k*-PCC) based on path-connectivity, which requires the path-connectivity of subgraph to be at least

*k*. Next, we further propose the steiner maximum path-connected component (SMPCC), which is the

*k*-PCC containing

*q*with the maximum path-connectivity. Finally, we design an efficient graph decomposition-based

*k*-PCC discovery algorithm, and based on this, propose an optimized SMPCC query algorithm. A large number of experiments on five real and synthetic HINs prove the effectiveness and efficiency of our proposed approaches.

*k*-路径连通分量;最大路径连通Steiner分量;元路径

*k*-path connected component;steiner maximum-path- connected component;meta-path