Original text discrimination method and device, equipment and computer readable storage medium

Abstract

The invention discloses an original text discrimination method, which comprises the following steps: after a to-be-discriminated text is received, obtaining more than one to-be-compared object corresponding to the to-be-discriminated text from a preset original database; preprocessing the text to be discriminated to obtain more than one first clause; comparing each first clause with each to-be-compared object, and determining a non-original clause existing in the first clause; and if the proportion of the non-original clause in the to-be-discriminated text is not greater than a preset plagiarism threshold, determining that the to-be-discriminated text is an original text. The invention furthermore discloses an original text discrimination device, equipment and a readable storage medium. The to-be-discriminated text is processed into the clauses, whether the to-be-discriminated text is the original text or not is determined and decomposed into whether the clauses are the original clauses or not, so that whether the to-be-discriminated text is the original text or not is determined according to the proportion of the original clauses, and the discrimination precision of the original text is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of financial technology (Fintech), in particular to an original text screening method, device, equipment and computer-readable storage medium. Background technique [0002] In recent years, with the continuous development of financial technology (Fintech), especially Internet finance, data screening technology has been introduced into the daily business of financial institutions such as banks. In the daily promotion process of financial institutions such as banks, in order to ensure that the promotional texts, such as news, soft articles and advertisements, do not plagiarize other people’s plagiarized works, the originality of the promotional texts needs to be reviewed before dissemination. Only by ensuring that the promotional texts are Original texts can avoid unnecessary copyright disputes and allow original works to receive due value feedback. Therefore, it is a must-do job for financial institut...

AI Technical Summary

Problems solved by technology

[0004] However, the existing method can only judge whether there is plagiarism in the text to be screened, but cannot give a specific index of plagiarism rate. If the text to be screened sequentially extracts a paragraph from multiple original texts, then the existing method cannot give a conclusion of plagiarism , and it is difficult to identify the originality of texts to be identified with a large number of subject substitutions and pronoun substitutions. Obviously, the accuracy of existing identification methods is low

Images