The huge and ever-increasing data traffic promotes the upgradation of IP bearer network to possess higher transmission capability. As a long-term task, network upgradation needs to be implemented in multiple stages. At each stage, one or more network partitions are planned to meet various requirements in different areas or periods to realize the smooth change from the current network to the targeted one. However, how to select proper network partitions is an open question. Existing approaches are usually infeasibly applied to large-scale networks or neglect the characteristics of IP bearer network. In this paper, we present a hierarchical community discovery method to find network partitions for nodes to be upgraded. We transform the issue of hierarchy identification on the whole network into node role classification, which is addressed by training a classifier utilizing network centrality, label, and attribute information. Then, a novel community detection algorithm through semi-local expansion is proposed, with the geographical location also taken into consideration. Experiments are conducted on three real-world datasets. The results show the effectiveness of our method in node role classification task that at least 90% Micro-F1 score can be got with only 30% labeled nodes on the given networks. The attained community is adjustable with the size proportional to the parameter $\alpha$ and has a high modularity score. Moreover, our communities strictly comply with the affiliation in IP bearer network and preserve the integrity of the tree/ring structures.

巨大且不断增长的数据流量促使IP承载网升级以具备更高的传输能力。网络升级是一项长期任务，需要分多个阶段实施。在每一阶段，规划一个或多个网络分区，以满足不同区域或时期的各种需求，实现从当前网络到目标网络的平滑变化。然而，如何选择合适的网络分区是一个悬而未决的问题。现有方法通常不适用于大规模网络或忽视IP承载网的特性。在本文中，我们提出了一种分层社区发现方法来为要升级的节点找到网络分区。我们将全网的层次识别问题转化为节点角色分类，这是通过利用网络中心性、标签和属性信息训练分类器来解决的。然后，提出了一种新的半局部扩展社区检测算法，同时考虑了地理位置。实验是在三个真实世界的数据集上进行的。结果表明我们的方法在节点角色分类任务中的有效性，在给定网络上仅 30% 的标记节点可以获得至少 90% 的 Micro-F1 分数。获得的社区可调整，大小与参数成正比 结果表明我们的方法在节点角色分类任务中的有效性，在给定网络上仅 30% 的标记节点可以获得至少 90% 的 Micro-F1 分数。获得的社区可调整，大小与参数成正比 结果表明我们的方法在节点角色分类任务中的有效性，在给定网络上仅 30% 的标记节点可以获得至少 90% 的 Micro-F1 分数。获得的社区可调整，大小与参数成正比$\alpha$并且具有很高的模块化分数。此外，我们的社区严格遵守 IP 承载网络的隶属关系，并保持树/环结构的完整性。