A method for incremental updating of SysML model recommendation results

By performing semantic parsing on the recommendation results of the SysML model and using a large language model to assist in decision-making, and generating a patch that minimizes discrepancies, the problems of redundancy and inconsistency in SysML model updates are solved, achieving efficient and accurate incremental updates and a personalized modeling experience.

CN122240159APending Publication Date: 2026-06-19HARBIN INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HARBIN INST OF TECH
Filing Date
2026-03-13
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing SysML model update methods suffer from redundancy, inconsistency, and high resource consumption. In particular, they cannot efficiently and accurately integrate recommendation results during incremental updates, resulting in bloated, inconsistent models and wasted computational resources.

Method used

By performing semantic parsing on the recommendation results of the SysML model, new or modified elements are identified. A large language model is used for intelligent judgment, generating a patch that minimizes the difference, and automatically applying it to the target model to ensure the accuracy and consistency of the update.

Benefits of technology

It enables efficient and accurate incremental updates of SysML models, reduces computational resource consumption, improves model consistency and development efficiency, and provides a personalized modeling experience and precise change management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122240159A_ABST
    Figure CN122240159A_ABST
Patent Text Reader

Abstract

This invention discloses an incremental update method for SysML model recommendation results. The method includes the following steps: Step S1: Load the original project to be incrementally updated, parse the file content, and establish element mapping; Step S2: Read the SysML recommendation result fragment into memory and parse it, analyze the namespace of the elements, treat elements in the UML / SysML namespace as model elements, and treat other namespaces as extended class elements; Step S3: Perform corresponding incremental update processing on each type of element according to its type; Step S4: Serialize and save the content after the incremental update and output it as a new project file. This invention significantly improves the efficiency and accuracy of SysML model incremental updates by combining a structural optimization algorithm with a large language model, ensuring accurate and efficient incremental updates in various complex scenarios.
Need to check novelty before this filing date? Find Prior Art