Nursing record processing method and system based on large language model

By adopting a nursing record processing method based on a large language model, the problems of low processing efficiency and low accuracy caused by the diversity of nursing record document formats are solved. It realizes automated processing and structured coding of multi-format documents, ensuring the standardization and accuracy of nursing records.

CN121636768APending Publication Date: 2026-03-10GENERAL HOSPITAL OF PLA
0 Cites 0 Cited by

Patent Information

Application Number
CN202511665079.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-13
Publication Date
2026-03-10

AI Technical Summary

Technical Problem

Nursing records are in the form of unstructured text, resulting in diverse data formats, difficulty in uniform processing, low efficiency and accuracy, lack of validation and terminology mapping mechanisms, and non-standard output.

Method used

A nursing record processing method based on a large language model was adopted, including preprocessing, hybrid retrieval, coding and terminology mapping. A large language model was constructed using the Deepseek framework, and iterative optimization was carried out in combination with a general nursing text database. A nursing professional dictionary and terminology database were introduced, and structured coding results were generated through hybrid retrieval and coding rules.

Benefits of technology

It has achieved automated processing of multi-format nursing documents, improved processing efficiency and accuracy, ensured that the coding results meet the standard specifications, suppressed the illusion problem of continuous model operation, and ensured the standardization and accuracy of the output.

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

Abstract

The invention belongs to the technical field of natural language processing, and discloses a nursing record processing method and system based on a large language model. The method comprises the following steps: preprocessing all nursing documents to obtain a preprocessed nursing document text comprising a plurality of clauses; performing candidate document matching on the plurality of preprocessed nursing document texts by using a mixed retrieval method to generate a final model input list; encoding the final model input list by using a large language model in combination with an encoding rule to obtain an encoding result; performing verification and term mapping on the coding result by using a large language model to obtain a structured coding result; and performing structured conversion on the structured coding result to obtain a structured result, and verifying the structured result and counting coding precision indexes in combination with a manually marked coding result. According to the invention, the problems of low efficiency, low accuracy and poor processing effect in the prior art are solved.
Need to check novelty before this filing date? Find Prior Art