公开(公告)号：US20240354222A1

公开(公告)日：2024-10-24

申请号：US18138330

申请日：2023-04-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： NAN DUAN ,  SHENGYU FU ,  SHUAI LU ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

IPC: G06F11/36 ,  G06N20/00

CPC classification number: G06F11/3636 ,  G06N20/00

Abstract: A large language model, previously pre-trained on multiple source code modeling tasks, is pre-trained, through curriculum learning, to learn to predict a code execution trace given a source code program. The model is pre-trained using a variety of pre-training datasets consisting of pairs of a source code sample and a corresponding execution trace. The curriculum pre-training starts with a pre-training dataset of single line executions and adds in additional pre-training datasets with more increasing complex behaviors. The pre-training datasets include mutation-augmented source code samples and their corresponding execution traces.

公开(公告)号：US20240160435A1

公开(公告)日：2024-05-16

申请号：US17985849

申请日：2022-11-12

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： NAN DUAN ,  SHENGYU FU ,  SHUAI LU ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

IPC: G06F8/71 ,  G06N3/08

CPC classification number: G06F8/71 ,  G06N3/08

Abstract: A deep learning model is pre-trained with a large-scale of unsupervised data of code review tasks in order to learn the relationships between code changes and a code review. The pre-trained deep learning model predicts a code review given a code diff hunk in a code diff format. The code diff hunk includes the changed code and its surrounding context. The pre-trained deep learning model may then be fine-tuned with supervised data in order to make predictions for several code review activities, such as, code change quality estimation and code refinement.

公开(公告)号：US20230359441A1

公开(公告)日：2023-11-09

申请号：US17740042

申请日：2022-05-09

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： NAN DUAN ,  SHUAI LU ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

IPC: G06F8/33 ,  G06F40/30 ,  G06N3/04

CPC classification number: G06F8/33 ,  G06F40/30 ,  G06N3/0454

Abstract: A retrieval-augmented code completion system uses the context of a partially-formed source code snippet of a source code program and a hint to predict the source code tokens needed to complete the partially-formed source code snippet. The hint is a source code segment that completes a semantically-similar source code segment of the partially-formed source code snippet. The hint is found in a retrieval source code database using a hybrid retrieval technique. A deep learning decoder model uses the context of the partially-formed source code snippet and the hint to predict the most likely candidate sequence of source code tokens to complete the partially-formed source code snippet.