Finding features in point clouds

I have some 3d point cloud data. (It's in fbx format but I can also get other formats including gltf, glb, usdz.) It's a scan of a building. I need someone who can apply some algorithms and machine learning to find different features in the point cloud. One example will be finding very small holes in the ceiling that can be used for hanging pipes or light fixtures. Another example might be segmentation of different parts/areas/features of the building. I want to make a simple "toy" demo (doesn't need to be 100% perfect) but I want it to use one or more advanced algorithms that go beyond trivial solutions.