Generating new software code from legacy software code using large language models
US12360791B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 29, 2024 |
| Grant date | Jul 15, 2025 |
| Priority date | — |
| Expiry date | Jul 29, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F8/51
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Computer-implemented systems and methods use a Large Language Model (LLM) for converting a legacy computer program in a first language to a human-language description of the legacy computer program, which description can be validated as being an accurate description of the legacy computer program. Once validated, the human-language description can be converted, again using an LLM, to a computer program in a target programming language. An LLM can also be used to generate test scripts for the new target-language program to test the performance of the target-language program in a production environment. An LLM can also be used to reconcile outputs from the legacy program to the new target program, such as on a function-by-function basis. If the differences between the outputs (if any) are sufficiently negligible, the legacy computer program can be decommissioned, and the new, target language program can be used in production.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.