AWS 用 Amazon Bedrock 将主机 Assembler 代码迁移为 Java
Modernizing mainframe Assembler to Java using Amazon Bedrock and AWS Transform
很多银行保险公司还在跑几十年前的 Assembler 代码,会写的人快退休了。AWS 这次给出的思路挺聪明:不直接转 Java,而是先转 COBOL 再转,准确率更高。工具用的是自家的 Bedrock 加 Kiro IDE,做遗留系统迁移的工程师可以照着这套流程抄作业。
AWS 发布了一套面向主机遗留系统的迁移方法,核心是用 Amazon Bedrock、Kiro IDE 和 AWS Transform 三件工具,把老旧的 Assembler 代码改写成 Java Spring Boot 应用。整个流程采用多阶段策略:先用 AI 从 Assembler 代码里提取业务规则,再借助中间 COBOL 阶段做转换,最后部署到 AWS 上运行。
选择先转 COBOL 再转 Java 是因为 Assembler 直接翻译成 Java 的语义偏差大,而 COBOL 与主机业务代码的语法和逻辑更接近,AI 转换的准确率更高。提取出的业务规则可以用来验证转换结果,Kiro IDE 则承担开发环境中的代码生成和修改工作。
主机 Assembler 应用长期面临维护成本高、懂这门语言的工程师稀缺的问题,这类方案对银行、保险等仍依赖主机系统的行业有直接参考价值,AWS 也借此把现代化迁移做成了自家工具链的组合拳。
Modernizing mainframe Assembler to Java using Amazon Bedrock and AWS Transform
Legacy mainframe Assembler applications are costly to maintain and hard to staff. This post presents a multi-stage, AI-powered methodology using Amazon Bedrock, Kiro IDE, and AWS Transform to extract business rules, convert Assembler through an intermediate COBOL stage, and deploy modernized Java Spring Boot applications on AWS.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, Kiro, AWS, code migration.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.