Methodology and Application
We study Intelligent Model-Driven Engineering as a methodology for precise, verifiable software construction and as an application framework for intelligent software factories.
Research Focus
Researching Intelligent Model-Driven Engineering is organized into two parts: methodology research, including DSL design and evaluation, and application research, including intelligent software factories and automated software development.
Methodology
We study Intelligent Model-Driven Engineering as a methodology: DSL design and evaluation, model definition, model transformation, AI-constrained generation, and verification-guided engineering workflows.
Application
We apply Intelligent Model-Driven Engineering to intelligent software factories and automated software development, turning models, agents, tools, scripts, and environments into repeatable production lines.
Methodology
The methodology part studies DSL design and evaluation, model definition, model transformation, generation constraints, agent workflows, and quality evaluation methods.
We study how domain-specific languages should be designed, evaluated, and evolved so that requirements, design decisions, constraints, deployment knowledge, and generation rules can be expressed precisely.
We define metamodels, graphical models, textual models, formal contracts, and model transformation rules that connect requirements, architecture, design, code, and deployment artifacts.
We combine model-driven precision with data-driven flexibility, using models as the engineering structure and generative AI as the adaptive driver for model and code generation.
We evaluate generated models and software artifacts through contracts, simulations, validation scripts, traceability evidence, and engineering quality measurements.
Application
The application part studies intelligent software factories and automated software development, where requirements, models, agents, generators, tests, release scripts, and deployment environments become repeatable engineering production lines.
A software factory assembles tools, models, workflows, scripts, environments, and quality gates into automated production lines for software development, build, test, release, and delivery.
We apply Intelligent Model-Driven Engineering to requirements extraction, model construction, prototype validation, architecture design, detailed design, code generation, deployment, and feedback-driven refinement.
RM2PT is studied as a full-lifecycle intelligent software factory for requirements refinement, validation, architecture generation, design optimization, code generation, and deployment.
We extend the approach to domain software factories such as HarmonyOS application generation, where GUI models, domain models, and AI-assisted code generation improve efficiency and quality.
01
Requirements model
02
Prototype validation
03
Architecture model
04
Design model
05
Code generation
06
Deployment and feedback
Research Progress
Intelligent Model-Driven Engineering has been evaluated through full-lifecycle RM2PT workflows and domain scenarios such as HarmonyOS application generation, where model-driven structures and AI generation are integrated.
~13x
faster requirements extraction and confirmation
2-10x
higher design productivity in evaluated workflows
61.92%
coding efficiency improvement in RM2PT studies
98%+
code correctness in HarmonyOS case validation
Capability Portfolio
The following projects are organized as reusable capability modules for Methodology and Application research in Intelligent Model-Driven Engineering.
From natural language, user stories, use cases, goals, problem frames, SysML, and UML to analyzable requirements and design models.
From OCL, formal contracts, validation scripts, generated inputs, and traceability evidence to quality-aware generation.
From requirements models to monolithic systems, microservices, enterprise information systems, DApps, GUI code, and domain applications.
Automated Requirement Elicitation
Model-driven tool support for intelligent software engineering workflows.
Model-driven tool support for intelligent software engineering workflows.
Model-driven tool support for intelligent software engineering workflows.
Model-driven tool support for intelligent software engineering workflows.
Model-driven tool support for intelligent software engineering workflows.
Automatic Generation SRS from Requirements Models
Automated Generation of UML from iStar Model
Problem Frames to UML
Automated Generation of Prototype Input for Rapid Requirements Validation
ChatGPT-enhanced Initialization Data Generation for Rapid Requirements Validation
A Tool for Automatic Generation of Validation Scripts to Support Rapid Requirements Validation
Automatic Generation of Natural Language from Object Constraint Language
Interactive Generation of Object Constraint Language from Natural Language
Object Constraint Language Generation from NL
Automatic Generation of Monolith Design from Requirements Model
Microservice Architecture Generation and Refinement from Requirements Model
Automatic Generation of MicroServices Architecture from Requirements Model
Automatic Generation of Enterprise Information System (SpringBoot-based Backend)
Automatic Generation of Enterprise Information System (Golang-based BackEnd)
Automatic Generation of Blockchain-based System (DApp)
Automatic Generation of Frontend GUI from Requirements Model