A multilingual document classification method, device and storage medium

Abstract

The present application provides a multilingual document classification method, device and storage medium. The multilingual document classification method includes the steps of: document reception, the document includes Chinese documents and foreign language documents; representative word extraction, according to the document content extraction There is at least one relative word for each document, and the representative words are clustered to obtain the representative words for the document; the document category table is received, and the document category table is provided with multiple bases Classification; document classification, the representative word is converted into a representative word vector, the basic category is converted into a class word vector, the correlation between the representative word vector and the class word vector is calculated, and the correlation is performed according to the correlation Classify the literature. Respectively extract representative words from the Chinese documents and foreign language documents, calculate the correlation between the representative word vector and the class word vector, classify the documents according to the correlation, and classify the Chinese documents and foreign language documents at the same time.

Description

technical field [0001] The present application relates to the technical field of information processing, and in particular to a multilingual document classification method, device and storage medium. Background technique [0002] With the rapid development of science and technology, a large number of scientific documents such as papers and patents continue to emerge. For some companies or enterprises, it is necessary to search in multiple network databases, so document search on the Internet can no longer meet the needs of these users. As a result, in the face of massive literature, more and more companies, enterprises, and groups have begun to build their own academic knowledge bases. [0003] However, building a knowledge base requires classifying documents, and then constructing the classified documents as a knowledge base. The documents in the network include Chinese documents and foreign language documents. Since Chinese documents and foreign language documents are doc...

AI Technical Summary

Problems solved by technology

[0003] However, building a knowledge base requires classifying documents, and then constructing the classified documents as a knowledge base. The documents in the network include Chinese documents and foreign language documents. Since Chinese documents and foreign language documents are documents in different languages, they cannot communicate with each other in language. , it is difficult to classify multilingual documents at the same time, so usually the academic knowledge base established by companies and enterprises is a single language knowledge base, and the scope of such knowledge base is limited

Images