Abstract: A device may receive global metadata terms and aliases, group level metadata terms and aliases, and user level metadata terms and aliases, and may generate global metadata graphs, group level metadata graphs, and user level metadata graphs. The device may train natural language understanding (NLU) models with the global metadata graphs, the group level metadata graphs, and the user level metadata graphs to generate trained NLU models, and may receive a search request from a user. The device may assign a level to the user and an identifier within the level based on a confidence and prior interactions associated with the user, and may select an NLU model from the trained NLU models based on the level and the identifier assigned to the user. The device may process the search request, with the NLU model, to generate search results, and may perform actions based on the search results.