Text tracing method and device and storage medium

Abstract

The embodiment of the invention relates to a text tracing method and device and a storage medium, and the method comprises the steps: generating a word bag model according to a to-be-judged text and asource text, the source text comprising a plurality of texts; Respectively carrying out similarity calculation on the word bag model by utilizing a plurality of preset similarity algorithms, and determining a plurality of first similarity sequences of a plurality of texts in the source text and the to-be-judged text under the condition of different similarity algorithms; Determining a second similarity sequence of a plurality of texts in the source text source text and the to-be-judged text based on a first formula and the first similarity sequence; And selecting the text meeting the homologycondition from the source text as the homology text of the to-be-judged text based on the second similarity order, and adopting multiple similarity algorithms to make up for the deficiency of a single algorithm, thereby reducing the contingency caused by different calculation modes, and improving the comprehensiveness and accuracy of the calculation result.

Description

technical field [0001] Embodiments of the present invention relate to the field of text data processing, and in particular, to a text source tracing method, device, and storage medium. Background technique [0002] Text traceability is mainly used in academic integrity detection, search engine optimization and other fields. The purpose is to judge whether the content of a text is copied or adapted from another or multiple texts. The principle of obtaining homologous texts is mainly based on the comparison of text similarity for judgment. [0003] In existing schemes, Jaccard similarity or cosine similarity comparison is usually used for text tracing. Jaccard similarity is a method to measure the similarity and difference between limited sample sets. The Jaccard coefficient is defined as comparing the two The ratio of the intersection and union of , the larger the value, the higher the similarity; the cosine similarity measures the difference between the two vectors by calcu...

AI Technical Summary

Problems solved by technology

[0004] However, the Jaccard similarity is not sensitive to the word frequency response of the same similar word, and the cosine similarity can make a sensitive judgment on the direction of the vector, but it cannot make a sensitive judgment on the digital data

[0005] Therefore, the function of the existing text similarity comparison method is relatively single, and it can only make accurate judgments in one aspect, but cannot compare all aspects of the text, resulting in inaccurate final results

Images