Multi-Agent collaboration AADL model AGREE verification statement automatic generation and verification method

The AADL model AGREE verification system, which utilizes multi-agent collaboration, addresses the lack of automation in the collaborative application of AADL models and AGREE specifications. It achieves an end-to-end pipeline from natural language requirements to verification results, thereby improving the efficiency and quality of complex embedded system development.

CN121706100APending Publication Date: 2026-03-20HARBIN UNIV
0 Cites 1 Cited by

Patent Information

Application Number
CN202511828154.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-05
Publication Date
2026-03-20

AI Technical Summary

Technical Problem

In existing technologies, the collaborative application of AADL models and AGREE specifications suffers from insufficient automation capabilities in complex systems, resulting in long design iteration cycles, excessive manual intervention, difficulty in achieving closed-loop feedback of modeling-analysis-optimization, and a lack of automated toolchains for multi-role collaboration, which increases the complexity and cost of formal verification.

Method used

A multi-agent collaborative AADL model AGREE verification system is constructed. By building a domain knowledge base and integrating AADL and AGREE specifications, a formal verification automated process is built using multi-agent collaboration. This achieves an end-to-end pipeline from natural language requirements to verification results, including steps such as model analysis, requirement decomposition, AGREE generation, and model fusion. RAG technology is used to generate AGREE attachment code and perform iterative verification.

Benefits of technology

It significantly improves the accuracy and verification efficiency of AGREE specification generation, reduces reliance on domain experts, and achieves full-process automation from natural language requirements to formal verification results, thereby improving the quality and efficiency of complex embedded system development.

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

Abstract

The invention discloses a multi-Agent cooperation AADL model AGREE verification statement automatic generation and verification method. The method comprises the following steps: S1, constructing a domain knowledge base; s2, the Agent is analyzed by the AADL model to extract key information; s3, the demand analysis Agent splits atomic propositions from the natural language demand; s4, the AGREE generator Agent generates an AGREE attachment code; s5, the model fusion Agent automatically embeds the AGREE specification into the target AADL component; s6, the AADL verification Agent performs iterative verification and automatic repair, and a multi-dimensional verification system is constructed; and S7, executing AGREE-based AADL architecture formalized verification, and performing logic attribute verification on the grammar compliance model. According to the invention, innovative fusion of a formalized verification method and an intelligent technology is realized, and the core problem that formalized verification of the AADL architecture is difficult to implement is effectively solved.
Need to check novelty before this filing date? Find Prior Art