Method and system for document classification
AssigneeMing Chuan University
InventorsYang-Cheng Lu, Jen-Nan Chen, Yu-Chen Wei
Life of this patent
Estimating the term…
Abstract
The present invention provides a method for document classification, especially an adaptive learning method for document classification. The document includes a plurality of feature words. The method includes steps of calculating a plurality of similarities between the document and a categorical basic knowledge; calculating a first ratio of a first largest similarity to a second largest similarity of the plurality of similarities; storing the feature words of the document as an extensive categorical knowledge when the first ratio is larger than a first threshold value; and updating the categorical basic knowledge by using the extensive categorical knowledge.
Claims15
A method for classifying a document including a plurality of feature words, the method comprising steps of:
- calculating a plurality of similarities between the document and a categorical basic knowledge;
- calculating a first ratio of a first largest similarity to a second largest similarity of the plurality of similarities;
- storing the feature words of the document as an extensive categorical knowledge when the first ratio is larger than a first threshold value;
- and
- updating the categorical basic knowledge by using the extensive categorical knowledge.
A system for classifying a document comprising a plurality of feature words, the system comprising:
- a processing unit calculating a plurality of similarities between the document and a categorical basic knowledge and calculating a ratio of a first largest similarity to a second largest similarity of the plurality of similarities;
- and
- a first buffer unit storing the plurality of feature words of the document as an extensive categorical knowledge when the ratio is larger than a threshold value, wherein the processing unit updates the categorical basic knowledge by means of the buffer unit.
A method for updating a categorical basic knowledge, comprising steps of:
- providing a plurality of feature words and the categorical basic knowledge;
- calculating a plurality of similarities between the feature words and the categorical basic knowledge;
- and
- updating the categorical basic knowledge according to the plurality of similarities.
Dependencies are inferred from the claim text.