Abstract: In some aspects, the techniques described herein relate to a method including: receiving, from a query interface, a natural language query; encoding the natural language query into tokens; embedding the tokens into a natural language query vector, wherein the natural language query vector represents a semantic meaning of the natural language query; formatting an index query of an index datastore, wherein the index query includes the natural language query vector as a lookup parameter of the index query; receiving, as a response to the index query, a document set; passing the document set and the natural language query to a machine learning model; receiving a response to the natural language query from the machine learning model, wherein the response is based on the document set; and providing the response to the natural language query to the query interface for consumption.

Abstract: In some aspects, the techniques described herein relate to a method performed by a graph enrichment platform, including: receiving an unstructured data object; extracting a fact from the data object, in the form of a subject, a predicate and an object; generating a first new node, a second new node, and a first new edge from the data object; assigning properties to the first new node, the second new node, and the first new edge; predicting a second new edge, wherein the second new edge connects one of the first new node or the second new node to an existing node in the knowledge graph; preparing a graph update, wherein the graph update includes the first new node, the second new node, the first new edge, and the second new edge; performing a conflict check on the graph update; and pushing the graph update to the knowledge graph.

Abstract: In some aspects, the techniques described herein relate to a method including: embedding a graph with an embedding model, wherein the embedding generates node and edge vectors for each node and each edge, respectively, in the graph; generating peer node groups based on the node vectors and the edge vectors; generating edge predictions based on the node vectors and the edge vectors; training a machine learning model based on the node vectors and the edge vectors; inputting the node vectors and the edge vectors into the machine learning model; receiving, as output from the machine learning model, a prediction of a future action based on the node vectors and the edge vectors; generating a plurality of insights based on the peer node groups, the edge predictions, and the prediction of a future action; storing the plurality of insights in an insight database, and providing an interface to the insight database.