Tibetan language thesis copying detection method and Tibetan language thesis copying detection system based on Tibetan language sentence levels

Abstract

The invention discloses a Tibetan language thesis copying detection method and a Tibetan language thesis copying detection system based on Tibetan language sentence levels. The Tibetan language thesis copying detection method includes: subjecting Tibetan language text characters to code conversion and noise removal preprocessing; segmenting a text into text blocks according to sentences through boundary identification of Tibetan language sentences and establishing a temporary table of segmented text blocks; extracting and computing text features from a sentence-document inverted index table and the temporary table according to the number of the sentences to obtain sentence similarity; establishing an adjacency list in accordance with the sentence similarity, computing text block similarity and detecting copying of two Tibetan language theses according to a text block similarity value. The Tibetan language thesis copying detection system comprises a Tibetan language thesis copying detection device and a database, wherein the Tibetan language thesis copying detection device is connected to a client terminal server through the Internet, and the database is connected to the server and used for storing Tibetan language theses. The Tibetan language thesis copying detection device comprises a preprocessing module for code conversion and noise removal of the text characters, a temporary table module for constructing the segmented text blocks, an extracting module for constructing sentence text features and a copying detection module for detecting whether the theses have similar copied data or not.

Description

technical field [0001] The invention belongs to the field of Tibetan language information processing, and in particular relates to a method and system for detecting the duplication of Tibetan texts based on Tibetan sentence levels. Background technique [0002] The definition of paper copy detection is to determine whether the content of a paper is plagiarized, plagiarized, or copied from another paper or papers. It mainly includes plagiarism methods such as complete copying, content shifting, synonym substitution, and rephrasing. Copy detection is sometimes called "plagiarism detection" or "plagiarism detection" specifically for academic papers. [0003] With the continuous development of the Internet and the increasing abundance of network digital resources, it has provided people with a convenient platform for resource sharing and information exchange. It has become an important source for people to obtain information, and at the same time provides a convenient academic...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problems of low detection efficiency and low detection accuracy in the existing technology relying on manual detection of plagiarized papers, the purpose of the present invention is to provide a Tibetan sentence-level-based detection method and system for copying Tibetan papers

Images