Medical text data synthesis method based on role driving

By introducing role-driven personalized processing and multi-level deduplication mechanisms, the problem of lack of targetedness and diversity in existing medical text data synthesis methods is solved, and high-quality and efficient medical text data generation is achieved.

CN119646164AActive Publication Date: 2025-03-18NINGBO BODEN AI TECHNOLOGY CO LTD
5 Cites 3 Cited by

Patent Information

Application Number
CN202510162116.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-14
Publication Date
2025-03-18
Estimated Expiration
2045-02-14

AI Technical Summary

Technical Problem

The existing medical text data synthesis methods lack role-driven personalized processing, resulting in the lack of targetedness and diversity of the generated data, the data redundancy and duplication problems, the screening mechanism is incomplete, and the problem type is single.

Method used

Introduce role-driven personalized processing, generate interest content based on the occupations and concerns of different medical roles, adopt multi-level deduplication mechanism and large language model to generate problems, combine semantics and correlation deduplication to ensure the diversity and practicality of the content.

Benefits of technology

It improves the personalization and pertinence of data, enhances the quality and deduplication efficiency of data, enriches the types of problems, optimizes the generated content, and fully covers various information needs of medical text data.

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

Abstract

The invention discloses a medical text data synthesis method based on role driving, and relates to the technical field of text data synthesis and artificial intelligence, and the method comprises the following steps: S100, generating an original problem; s200, screening original problems; and S300, synthesizing the medical text data. According to role description and interest content generation, the adaptability to different medical role requirements is enhanced, semantic duplicate removal and correlation evaluation are realized by utilizing a text coding model and a vector database, semantic duplicate content is removed, correlation is accurately evaluated by utilizing a large language model, the data quality and diversity are improved, and the method is suitable for popularization and application. Through generation of variant questions and answers, diversity and practicability of medical text data are enriched. According to the method, the personalization and pertinence of the medical text data are improved, the quality and duplicate removal efficiency of the medical text data are enhanced, the problem types are enriched, the generated content is optimized, and various information requirements of the medical text data are comprehensively covered.
Need to check novelty before this filing date? Find Prior Art