US 7,519,565 B2 · Methods and apparatuses for classifying electronic documents

Abstract

Embodiments of the invention provide methods and apparatuses for classifying electronic documents (e.g., electronic communications) as either spam electronic documents or legitimate electronic documents. In accordance with one embodiment of the invention, each of a plurality of electronic communications is reduced to a corresponding multidimensional vector based on a multi-dimensional vector space. The multi-dimensional vectors represent corresponding electronic documents that have been classified as at least one type of electronic documents. Subsequent electronic documents to be classified are reduced to a corresponding multi-dimensional vector inserted into the multi-dimensional vector space. The electronic documents corresponding to an inserted multi-dimensional vector are classified based upon the proximity of the inserted multi-dimensional vector to at least one previously classified multi-dimensional vectors of the multi-dimensional vector space.

Claims84

Dependent claims

A method comprising:

defining a multi-dimensional vector space, the definition based upon a knowledge of a classification;
populating the multi-dimensional vector space with at least one known vector associated with an at least one feature that includes a feature weighting based on a differentiation capacity of the at least one feature, the differentiation capacity indicating whether the at least one feature occurs predominately in spam or non-spam electronic documents;
reducing an electronic document to a corresponding multi-dimensional vector based upon the multi-dimensional vector space;
classifying the electronic document as being a spam or a non-spam electronic document in regard to the populated multi-dimensional vector space, based on a distance between the corresponding multi-dimensional vector and the at least one vector, wherein the distance is based on the feature weighting;
and
outputting the electronic document to a receiver based on classifying the electronic document as being spam or non-spam.

3 more elements

A machine-readable medium having stored thereon a set of instructions which when executed cause a system to perform a method comprising:

defining a multi-dimensional vector space, the definition based upon a knowledge of a classification;
populating the multi-dimensional vector space with at least one known vector associated with an at least one feature that includes a feature weighting based on a differentiation capacity of the at least one feature, the differentiation capacity indicating whether the at least one feature occurs predominately in spam or non-spam electronic documents;
reducing an electronic document to a corresponding multi-dimensional vector based upon the multi-dimensional vector space;
classifying the electronic document as being a spam or a non-spam electronic document in regard to the populated multi-dimensional vector space, based on a distance between the corresponding multi-dimensional vector and the at least one vector, wherein the distance is based on the feature weighting;
and
outputting the electronic document to a receiver based on classifying the electronic document as being spam or non-spam.

3 more elements

A system comprising:

a processor;
a network interface coupled to the processor;
and
a machine-readable medium having stored thereon a set of instructions which when executed cause the system to perform a method comprising:
defining a multi-dimensional vector space, the definition based upon a knowledge of a classification;
populating the multi-dimensional vector space with at least one known vector associated with an at least one feature that includes a feature weighting based on a differentiation capacity of the at least one feature, the differentiation capacity indicating whether the at least one feature occurs predominately in spam or non-spam electronic documents;
reducing an electronic document to a corresponding multi-dimensional vector based upon the multi-dimensional vector space;
classifying the electronic document as being a spam or a non-spam electronic document in regard to the populated multi-dimensional vector space, based on a distance between the corresponding multi-dimensional vector and the at least one vector, wherein the distance is based on the feature weighting;
and
outputting the electronic document to a receiver based on classifying the electronic document as being spam or non-spam.

7 more elements

Dependencies are inferred from the claim text.

Methods and apparatuses for classifying electronic documents

Life of this patent

Methods and apparatuses for classifying electronic documents

Life of this patent

Abstract

Claims84