Deep data classification using governance and machine learning
AssigneeInternational Business Machines Corporation
InventorsNeerju Neerju, Kunjavihari Madhav Kashalikar, Namit Kabra, Likhitha Maddirala
Life of this patent
Estimating the term…
Abstract
A method of data classification includes: identifying a cluster of data classes; classifying columns of a current data set; identifying the cluster in the current data set; determining, based on the cluster, an expected column is missing from the current data set; determining a neighboring data set; identifying the expected column in the neighboring data set; classifying the expected column in the neighboring data set; creating a new data class in the current data set; and classifying an unclassified column in the current data set or the neighboring data set with the new data class.
Claims20
A method, comprising:
- identifying, by a computing device, a cluster of data classes;
- classifying, by the computing device, columns of a current data set;
- identifying, by the computing device, the cluster in the current data set;
- determining, by the computing device and based on the cluster, an expected column is missing from the current data set;
- determining, by the computing device, a neighboring data set;
- identifying, by the computing device, the expected column in the neighboring data set;
- and
- classifying, by the computing device, the expected column in the neighboring data set.
A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
- identify a cluster of data classes;
- classify columns of a current data set;
- identify the cluster in the current data set;
- determine, based on the cluster, an expected column is missing from the current data set;
- determine a neighboring data set;
- identify the expected column in the neighboring data set;
- classify the expected column in the neighboring data set;
- create a new data class in the current data set;
- and
- classify an unclassified column in the current data set or the neighboring data set with the new data class.
A system comprising:
- a processor, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
- identify a cluster of data classes;
- classify columns of a current data set;
- identify the cluster in the current data set;
- determine, based on the cluster, an expected column is missing from the current data set;
- determine a neighboring data set;
- identify the expected column in the neighboring data set;
- classify the expected column in the neighboring data set;
- create a new data class in the current data set;
- and
- classify an unclassified column in the current data set or the neighboring data set with the new data class.
Dependencies are inferred from the claim text.