Pattern recognition using nlp-based tokenizing and clustering models

Abstract

A system for interaction pattern recognition receives an input primary interaction and accesses clusters indicating interaction group patterns. Each cluster includes a respective primary interaction and secondary interactions linked to that primary interaction. Each cluster is identified by a respective non-fungible token. The system then determines a non-fungible token of the input primary interaction, compares it to the non-fungible tokens of the clusters, selects a first cluster based on a match between the non-fungible token of the input primary interaction and a first non-fungible token identifying the first cluster, determines the secondary interactions in the first cluster as linked to the input primary interaction, retrieves the secondary interactions from the clusters, generates a recommended group of interactions including the input primary interaction and the retrieved secondary interactions, and provides the recommended group of interactions and an indication that the retrieved secondary interactions are linked to the input primary interaction.