AUTOMATED DOCUMENT CLUSTER MERGING FOR TOPIC-BASED DIGITAL ASSISTANT INTERPRETATION

摘要

Disclosed are systems and techniques for extracting discovered topics from determined discourse clusters for the generation of a language model for interpreting commands received from a digital assistant device. An electronic document corpus can be generated having documents clustered based on entropy, among other things. The clusters can be associated with a corresponding plurality of cluster attractors that are representative of a context of the documents included therein. The documents within the clusters can be analyzed, so that clusters determined representative of a hierarchical discourse community can be determined and merged. The merged clusters can be analyzed, such that topics and/or sub-topics can be determined and extracted therefrom, indexed, and stored, among other things. In this way, a more efficient searching of the electronic document corpus to interpret received inputs, such as commands received via a digital assistant device, can be facilitated.