Method, device and equipment for checking duplicate of product standard document

Abstract

The invention relates to the technical field of text duplicate checking, and discloses a duplicate checking method, device and equipment for product standard documents, and the method comprises the following steps: for each related product standard document, carrying out text extraction on a plurality of parts of the related product standard document to obtain related part texts; constructing a plurality of duplicate checking databases based on the related part text of each related product standard document; performing text extraction on a plurality of parts of the target product standard document to obtain a target part text; and performing duplicate checking based on the target part text of the target product standard document by adopting the plurality of duplicate checking databases to obtain a duplicate checking result. According to the method, through partial processing, the duplicate checking key point is placed on the key part, the pertinence of duplicate checking is remarkably improved, the design of multiple duplicate checking databases is adopted, the core difference between the product standard documents can be more accurately recognized, the whole duplicate checking process is designed according to the characteristics of the product standard documents, it is ensured that the actual requirements can be met, and the practicability is high. And meanwhile, the duplicate checking accuracy is improved.

Images