Patent · US Active

Semantic data type classification in rectangular datasets

US11556514B2 · kind B2 · utility

1Cited by
4References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 24, 2021
Grant dateJan 17, 2023
Priority date
Expiry dateApr 17, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V30/413
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Provided is a method, computer program product, and system for automatically predicting unknown semantic data types in a rectangular dataset using a holistic knowledge of said dataset. A processor may receive one or more rectangular datasets, the one or more rectangular datasets comprising a plurality of columns having a set of known semantic data types. The processor may extract a set of features from the plurality of columns, where the set of features is used to determine a relationship among each column of the plurality of columns. The processor may construct a set of training data based on the extracted set of features. Using the training data, the processor may train a machine learning model to predict a semantic data type of a target column in a rectangular dataset having an unknown semantic data type.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.