Geological text translation method based on large language model and retrieval enhancement generation

By creating geological text naming entity labeling corpus and syntactic perceptual data enhancement methods, the large language model is fine-tuned, combined with geological dictionary database and search enhancement technology, the lack of professional knowledge in training data in geological text translation is solved, and high-quality geological text translation is achieved.

CN120409502AActive Publication Date: 2025-08-01SUN YAT SEN UNIV
2 Cites 3 Cited by

Patent Information

Application Number
CN202510867309.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-26
Publication Date
2025-08-01
Estimated Expiration
2045-06-26

AI Technical Summary

Technical Problem

The prior art has hallucinations caused by lack of professional domain knowledge in geological text translation, and Chinese named entity recognition performs poorly in complex contexts and long-distance dependencies, especially in nested entity recognition and cross-language processing.

Method used

By creating a physical labeling corpus in Chinese and English geological texts, a syntactic-aware entity pruning data enhancement method is used to fine-tune the large language model, and a geological dictionary database with category label information is constructed, combining search enhancement generation and translation technology to achieve accurate translation of geological text.

Benefits of technology

It improves the accuracy of naming entity recognition and translation accuracy, reduces the hallucination problem of large language models due to lack of professional knowledge due to training data, and improves the quality and reliability of geological text translation.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a geological text translation method based on a large language model and retrieval enhancement generation, and aims to identify a geological text named entity as a keyword and retrieve and query a professional dictionary database to perform enhancement translation. According to the method, when entity recognition is carried out on a fine tuning large language model, a syntax-aware entity pruning (SAEP) method is provided for data enhancement, controllable noise is introduced, and the named entity recognition effect of the large language model is improved. When a vector database is constructed and retrieved, geological classification labels are added to data information based on a data level, and a data similarity query threshold value is set, so that the accuracy of information retrieval is improved, and the illusion problem of a general large language model caused by the lack of professional domain knowledge of training data is effectively reduced.
Need to check novelty before this filing date? Find Prior Art