Deep learning and neural network has been widely used in research, deep learning has empowered many tasks such as point clouds segmentation and shape recognition. One of the main advantages of deep interaction point cloud segmentation is that it allows the feature extraction can be learned through neural network based on a large amount of dataset. Our focus is large point clouds, we propose a variety of measuring tools to analyze and validate raw point cloud data, which is the web-based deep segmentation user interaction on large point clouds. It allows users to view data sets with millions of points, from sources such as building structure and indoor scene, in standard web browsers, and processing 3D point clouds deep segmentation with the neural network. The interaction tools can assist to distinguish building structure and non-building structure in one room.