Multi-modal program inference
US11934801B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 7, 2021 |
| Grant date | Mar 19, 2024 |
| Priority date | — |
| Expiry date | Apr 7, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/40
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments use a multi-modal approach to generate software programs that match a solution program description. The solution program description may include natural language, input-output examples, partial source code, desired operators, or other hints. Some embodiments use optimized prompts to a pre-trained language model to obtain initial candidate programs. Maximal program components are extracted and then recombined variously using component-based synthesis. Beam search reduces a solution program search space by discarding some candidates from a given synthesis iteration. Relevance metrics, string similarity metrics, operator frequency distributions, token rareness scores, and other optimizations may be employed. By virtue of optimizations and the multi-modal approach, a solution program may be obtained after fewer iterations than by use of a language model alone. The multi-modal approach is domain agnostic, as illustrated by examples using regular expression and cascading style sheet selector domain specific languages.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.