Determining data categorizations based on an ontology and a machine-learning model

A method comprising:

• determining, by one or more computing devices and for a dataset, a tag associated with the dataset and a description associated with the dataset;
• determining, by the one or more computing devices, an ontology-based data type category and an ontology-based confidentiality category, by searching, using search data based on the tag and the description, an ontology that includes first associations between words and a plurality of data type categories and second associations between the plurality of data type categories and a plurality of confidentiality categories, wherein the plurality of confidentiality categories indicate whether data is subject to a data confidentiality procedure;
• determining, by the one or more computing devices, a model-based data type category and a model-based confidentiality category by using, based on the tag and the description, a model configured to output, based on tags and descriptions, data type categories and confidentiality categories;
• determining, by the one or more computing devices and based on the ontology-based data type category and the model-based data type category, a data type category associated with the dataset;
• determining, by the one or more computing devices and based on the ontology-based confidentiality category and the model-based confidentiality category, a confidentiality category associated with the dataset;
• and
• modifying, by the one or more computing devices, the dataset to indicate the data type category and the confidentiality category.

An apparatus comprising:

• one or more processors;
• and
• memory storing executable instructions that, when executed by the one or more processors, cause the apparatus to:
• determine, for a dataset, a tag associated with the dataset and a description associated with the dataset, wherein the dataset is associated with a pre-existing data type category and a pre-existing confidentiality category;
• determine an ontology-based data type category and an ontology-based confidentiality category by searching, using search data based on the tag and the description, an ontology that includes first associations between words and a plurality of data type categories and second associations between the plurality of data type categories and one or more confidentiality categories;
• determine a model-based data type category and a model-based confidentiality category by using, based on the tag and the description, a model configured to output, based on tags and descriptions, data type categories and confidentiality categories;
• determine, based on the ontology-based data type category and the model-based data type category, a data type category associated with the dataset;
• determine, based on the ontology-based confidentiality category and the model-based confidentiality category, a confidentiality category associated with the dataset;
• determine, based on the data type category, whether the pre-existing data type category is validated;
• determine, based on the confidentiality category, whether the pre-existing confidentiality category is validated;
• and
• send one or more indications of whether the pre-existing data type category and the pre-existing confidentiality category are validated.