公开(公告)号：US20230176829A1

公开(公告)日：2023-06-08

申请号：US17544502

申请日：2021-12-07

Applicant: Microsoft Technology Licensing, LLC

Inventor： Kiarash RAHMANI ,  Mohammad RAZA ,  Sumit GULWANI ,  Vu Minh LE ,  Daniel James MORRIS ,  Arjun RADHAKRISHNA ,  Gustavo ARAUJO SOARES ,  Ashish TIWARI

IPC: G06F8/33 ,  G06F40/40 ,  G06F8/38 ,  G06F40/30 ,  G06F8/10

CPC classification number: G06F8/33 ,  G06F40/40 ,  G06F8/38 ,  G06F40/30 ,  G06F8/10

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.