SYSTEM AND METHOD FOR CLASSIFYING AN ALPHANUMERIC CANDIDATE IDENTIFIED IN AN EMAIL MESSAGE

摘要

A technique for classifying an alphanumeric candidate in an email message can include receiving and parsing a plurality of email messages to identify at least one alphanumeric candidate. For each particular alphanumeric candidate, the technique can include: (i) associating the particular alphanumeric candidate with an originating email in which the particular alphanumeric candidate was identified, and (ii) determining email specific, recipient specific, and recipient agnostic features pertaining to the particular alphanumeric candidate. The alphanumeric candidates can be clustered based on the email specific, the recipient specific, and the recipient agnostic features to generate a plurality of clusters, with which an alphanumeric candidate type can be associated. The technique can include training an alphanumeric candidate type classifier based on the plurality of clusters and the associated alphanumeric candidate types, which can be utilized to determine the type of an unclassified alphanumeric candidate in a later received email message.