Data classification method and system, and related apparatus

Abstract

The present application discloses a data classification method and system, and a related apparatus, for use in performing quick and accurate classification on data. The method of the present application comprises: acquiring data source information, and performing data extraction on the data source information to obtain target data; acquiring a full subject thesaurus and a departmental subject thesaurus; on the basis of the full subject thesaurus, determining whether the target data has a subject; if yes, extracting the subject from the full subject thesaurus; if no, classifying the target data by means of a preset learning model so as to obtain a data classification result; when the target data has a subject, determining whether the subject is unique; if yes, taking the subject as the data classification result; if no, determining a departmental subject of the target data on the basis of the departmental subject thesaurus; when the subject is not unique, determining whether the subject overlaps the departmental subject; if yes, taking the subject or the departmental subject as the data classification result; if no, classifying the subject and the departmental subject by means of the preset learning model so as to obtain a data classification result.

Images