Domain name classification systems and methods

A system, comprising:

• a processor;
• a non-transitory computer-readable medium;
• and
• instructions stored on the non-transitory computer-readable medium and translatable by the processor for:
• obtaining a domain name, a seed value, and an identification of a substring of the domain name that is relevant match to the seed value;
• determining key-value pairs that encode information about terms in substrings of the domain name, the terms including a term in the substring of the domain name, wherein the determining comprises:
• obtaining a language model for the term in the substring of the domain name;
• analyzing a cluster of language models closest to the language model for the term in the substring of the domain name, wherein the analyzing the cluster of language models comprises analyzing a plurality of language models within a predetermined threshold distance from the language model for the term in the substring of the domain name;
• and
• determining, based on the analyzing, a relevance of the term in the substring of the domain name to the seed value;
• and
• providing the relevance of the term in the substring of the domain name to the seed value to a computing device.

A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor for:

• obtaining a domain name, a seed value, and an identification of a substring of the domain name that is relevant match to the seed value;
• determining key-value pairs that encode information about terms in substrings of the domain name, the terms including a term in the substring of the domain name, wherein the determining comprises:
• obtaining a language model for the term in the substring of the domain name;
• analyzing a cluster of language models closest to the language model for the term in the substring of the domain name, wherein the analyzing the cluster of language models comprises analyzing a plurality of language models within a predetermined threshold distance from the language model for the term in the substring of the domain name;
• and
• determining, based on the analyzing, a relevance of the term in the substring of the domain name to the seed value;
• and
• providing the relevance of the term in the substring of the domain name to the seed value to a computing device.