Abstract: In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent contextual relationships among elements (e.g., based on proximity, functionality, parent-child relationships, etc.). During training, the GNN learns embeddings from the nodes and edges of the graph-structured data structures, the embeddings capturing contextual clues that distinguish between elements that may share similar geometry (e.g., cross section, volume, surface area, etc.), yet serve different purposes.

Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).

Abstract: In example embodiments, a software service may employ a neural network to learn a non-linear mapping that transforms element features into embeddings. The neural network may be trained to distribute the embeddings in multi-dimensional embedding space, such that distance between the embeddings is meaningful to the class or category classification, or property prediction, task at hand. The neural network may be trained using weakly supervised machine learning, using weakly labeled infrastructure models. Embeddings for groups may be used to determine prototypes. Elements of an infrastructure model may be classified into classes or categories, or their properties predicted, as the case may be, by finding a nearest prototype.

Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).