A multimodal large model oracle-free entity relation extraction method

By fusing text, image, and HTML data into a multimodal large model, and combining it with the Oracle Bone Script knowledge system and constraint rules, the automatic extraction of zero-sample entity relationships from Oracle Bone Script was achieved. This solved the problems of low efficiency and poor accuracy in entity relationship extraction in the Oracle Bone Script field, and improved the intelligence and digitalization level of Oracle Bone Script research.

CN122309764APending Publication Date: 2026-06-30SANYA SCI & EDUCATION INNOVATION PARK WUHAN UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SANYA SCI & EDUCATION INNOVATION PARK WUHAN UNIV OF TECH
Filing Date
2026-05-29
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing technologies lack high-quality annotated corpora in the Oracle domain, making it difficult to meet the needs of entity relation extraction. Furthermore, the multimodal features of Oracle data are difficult to fully acquire, resulting in low efficiency and poor accuracy in entity relation extraction.

Method used

By employing a multimodal large model and combining text, image, and HTML data, and through large model prompting learning and efficient parameter fine-tuning, a zero-shot entity relationship extraction method is constructed. Utilizing the Oracle knowledge system and constraint rules, the method achieves automatic extraction and fusion of Oracle entity relationships.

Benefits of technology

It improves the accuracy, comprehensiveness, and generalization ability of Oracle entity relationship extraction, provides high-quality structured data support, and lays the foundation for Oracle knowledge graph construction and intelligent question answering tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122309764A_ABST
    Figure CN122309764A_ABST
Patent Text Reader

Abstract

This invention discloses a method for zero-shot entity relation extraction from oracle bone script using a multimodal large-scale model. First, multimodal oracle bone script data is collected and preprocessed. Then, an oracle bone script knowledge system is defined, and the multimodal data is labeled according to entity and relation categories. A multimodal labeled dataset is then constructed, divided into training and test sets. Next, a zero-shot entity relation extraction model is built, inputting the multimodal oracle bone script data from the training set into the model and outputting multimodal triples. Finally, a modality fusion model is constructed, inputting the multimodal triples into the model for multimodal information fusion, ultimately obtaining structured triples. This invention achieves zero-shot oracle bone script entity relation extraction by fusing text, image, and HTML multimodal information, combined with large-scale model prompting learning and efficient parameter fine-tuning techniques. This reduces dependence on labeled data and improves the accuracy, comprehensiveness, and generalization ability of the extraction results.
Need to check novelty before this filing date? Find Prior Art