Clustering and dynamic re-clustering of similar textual documents

A computer-implemented method comprising:

• receiving, by a prediction computational instance and from an end-user computational instance, a first textual record, wherein the end-user computational instance is dedicated to a managed network, and wherein the prediction computational instance and the end-user computational instance are both disposed within a remote network management platform;
• determining, by a machine learning (ML) clustering model of the prediction computational instance that represents a set of clusters of textual records, that the first textual record corresponds to a particular cluster selected from the set of clusters of textual records;
• transmitting, by the prediction computational instance and to the end-user computational instance, a representation of the particular cluster;
• receiving, by the prediction computational instance and from the end-user computational instance, a second textual record;
• determining, by the ML clustering model, that the second textual record does not correspond to any cluster of textual records of the set of clusters of textual records;
• responsive to determining that the second textual record does not correspond to any cluster of textual records of the set of clusters of textual records, adding, by the prediction computational instance, the second textual record to a stored set of residual textual records;
• identifying, by the prediction computational instance, an additional cluster of textual records based on the stored set of residual textual records;
• and
• transmitting, by the prediction computational instance and to the end-user computational instance, a representation of the additional cluster of textual records.

A computer-implemented method comprising:

• obtaining a plurality of textual records divided into clusters and a residual set of the textual records, wherein a machine learning (ML) clustering model divided the plurality of textual records based on a similarity metric;
• receiving, from a client device, a particular textual record representing a query;
• determining, by way of the ML clustering model and based on the similarity metric, that the particular textual record does not fit into any of the clusters;
• and
• in response to determining that the particular textual record does not fit into any of the clusters, adding the particular textual record to the residual set of the textual records.