US 2026/0259894 A1 · Clustering Key Selection Based on Machine-Learned Key Selection Models for Data Processing Service

Abstract

The disclosed configurations provide a method (and/or a computer-readable medium or system) for determining, from a table schema describing keys of a data table, one or more clustering keys that can be used to cluster data files of a data table. The method includes generating features for the data table, generating tokens from the features, generating a prediction for each token by applying to the token a machine-learned transformer model trained to predict a likelihood that the key associated with the token is a clustering key for the data table, determining clustering keys based on the predictions, and clustering data records of the data table into data files based on key-values for the clustering keys.

Claims20

Dependent claims

A computer-implemented method, comprising:

receiving, from a client device, a request to ingest one or more data files to a data table in a data storage system, the data table including values for one or more keys;
accessing a data classifier tree for the data table, the data classifier tree constructed using clustering keys and including nodes and edges, wherein the clustering keys are determined using a machine-learned model trained to determine, based on a name label for a given key of the data table and a data type associated with the given key, a likelihood that the given key of the data table is a clustering key for constructing the data classifier tree;
and
associating, in the data storage system, a data file of the one or more data files with a node of the data classifier tree.

1 more element

Dependencies are inferred from the claim text.

Clustering Key Selection Based on Machine-Learned Key Selection Models for Data Processing Service

Life of this patent

Clustering Key Selection Based on Machine-Learned Key Selection Models for Data Processing Service

Life of this patent

Abstract

Claims20