Document classification method and apparatus

Abstract

The invention provides a document classification method and apparatus. The method comprises the steps of obtaining a plurality of training documents and determining a type corresponding to each training document; according to the training document corresponding to each type, determining an eigenvector of each type, wherein the eigenvector comprises word strings occurring in the corresponding current type and an occurrence probability of each word string in the current type; obtaining a current to-be-classified document and extracting a matched eigenvector of the current to-be-classified document from the current to-be-classified document, wherein the matched eigenvector comprises to-be-matched word strings occurring in the current to-be-classified document; according to the to-be-matched word strings in the matched eigenvector and the occurrence probability in the eigenvector of each type, determining the similarity between the matched eigenvector and the eigenvector of each type; and taking a type corresponding to an eigenvector with the highest similarity as the type of the current to-be-classified document. According to the document classification method and apparatus provided by the invention, the document classification can be performed more flexibly.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for classifying documents. Background technique [0002] With the development of sustainable technology, natural language processing technology has received unprecedented attention and made great progress, and has developed into a relatively independent discipline that has attracted much attention. Now, with Internet +, big data and other popular concepts and With the attention of technology, various industries are making various attempts to make full use of webpage text data on the Internet, and natural language processing technology is the main force in these webpage text processing, analysis, and utilization tasks. [0003] In the prior art, the processing of webpage text data is mainly based on a preset and fixed classification method, which is difficult to adjust according to user requirements. For example, the accuracy rate of the classification resul...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the processing of webpage text data is mainly based on a preset and fixed classification method, which is difficult to adjust according to the needs of users

For example, the accuracy rate of classification results is difficult to meet the needs of users, but it is also difficult for users to adjust the classification method, which has reached the user's accuracy requirements

It can be seen from the above description that the classification methods in the prior art are not flexible enough

Images