Method for storing and retrieving translated document

Abstract

The invention provides a method for storing and retrieving a translated document. The method for storing and retrieving the translated document is characterized by comprising the first step of obtaining a translate manuscript base and a feature tag; the second step of forming a sentence list and conducting corpus alignment; the third step of conducting classified storage on corpus according to the feature tag; the fourth step of obtaining a manuscript to be translated and inputting a query tag; the fifth step of conducting sentence punctuating treatment on the manuscript to be translated to form the sentence list; the sixth step of setting a retrieval parameter to the manuscript to be translated, and conducting corpus retrieving and corpus matching in the translate manuscript base; the seventh step of recording complete matching times and fuzzy matching times, and then conducting weighted computation; the eighth step of obtaining a retrieved and matched result and displaying according to matching degree. The method for storing and retrieving the translated document has the advantages that a translator with a translating experience can be quickly positioned, then the translation reference file of the translator is returned, then sentences, terms, corpuses which are translated before are returned to the translator in a mode of a language pair, which brings convenience to the translator for reference, and thus the translating efficiency of the translator is improved.

Description

technical field [0001] The invention mainly relates to the technical field of artificial intelligence, and in particular to a method for storing and retrieving translated documents. Background technique [0002] After the translator completes the translation of the document, the translated document needs to be stored. The traditional storage method is to store the document according to different directory structures, and classify the document through the directory structure. When the translation document increases and the industry category increases, the directory structure will change. It is extremely complicated, it is very inconvenient to store, and it is difficult to locate the appropriate storage directory immediately; when a translation document needs to be retrieved, it takes a lot of time and manpower to find it, and after finding the translation document, you need to read The content of the document is manually searched for common sentences, terms, and corpus in the...

AI Technical Summary

Problems solved by technology

[0002] After the translator completes the translation of the document, the translated document needs to be stored. The traditional storage method is to store the document according to different directory structures, and classify the document through the directory structure. When the translation document increases and the industry category increases, the directory structure will change. It is extremely complicated, it is very inconvenient to store, and it is difficult to locate the appropriate storage directory immediately; when a translation document needs to be retrieved, it takes a lot of time and manpower to find it, and after finding the translation document, you need to read The content of the document is manually searched for common sentences, terms, and corpus in the document, and then provided to translators for reference and application; this traditional method has low storage efficiency and complex storage structure, which is not conducive to machine storage and retrieval, and Retrieval requires a lot of manpower and a lot of time to participate in order to obtain limited common sentences, terms and corpus

Images