Shao W Deng

US Patent:

20220358286, Nov 10, 2022

Filed:

Apr 22, 2021

Appl. No.:

17/237936

Inventors:

- Redmond WA, US
Jonathan Keith SIMMONS - Sammamish WA, US
David Ellis PUGH - Bellevue WA, US
Vivian Julia LIM - Redmond WA, US
Anqi LI - Redmond WA, US
Shwetha SRINATH - Bellevue WA, US
German David OBANDO CHACON - Kirkland WA, US
Jin Woo JANG - Seattle WA, US
Shengyu FU - Redmond WA, US
Shao Kun DENG - Bellevue WA, US

International Classification:

G06F 40/274
G06F 40/166
G06F 8/33
G06F 40/284

Abstract:

Edit automation enhancements may be implemented in source code editors and other text editors. Provisional selections that indicate user intentions are submitted to a suggestion generator with other edit context information, to improve the quality of generated text suggestions and reduce the cognitive load on users. A provisional selection may include a highlighted completion list entry, or document text targeted by a hovering cursor, or metainformation text targeted by the hovering cursor, for example. An inline grey text suggestion driven by provisional selection may be displayed simultaneously with completion list suggestions that were created without regard to provisional selection. Suggestions driven by provisional selection may be interleaved with existing document text. Suggestions may be accepted fully in one gesture, or in parts. Suggestions may be edited by a user before being accepted, driving further suggestion refinement. Multiple suggestions may be displayed simultaneously, reducing pressure on the suggestion generator.

US Patent:

20230128008, Apr 27, 2023

Filed:

Oct 22, 2021

Appl. No.:

17/508097

Inventors:

- Redmond WA, US
SHAO KUN DENG - BELLEVUE WA, US
NEELAKANTAN SUNDARESAN - BELLEVUE WA, US
MICHELE TUFANO - BELLEVUE WA, US

International Classification:

G06F 11/36
G06F 8/77
G06F 8/41
G06N 3/04
G06N 3/08

Abstract:

A test-driven development system utilizes a neural transformer model with attention to generate method bodies for a focal method given its associated test cases, and optionally a method signature and a docstring of the focal method. The candidate method bodies are validated for syntactic correctness, tested using the given test cases, and tested with a donor class in a target system. Those candidate method bodies passing the validation and testing are then ranked based on a PLUM score that analyzes the candidate method bodies against various quality and performance metrics.

US Patent:

20210034335, Feb 4, 2021

Filed:

Nov 11, 2019

Appl. No.:

16/680328

Inventors:

- Redmond WA, US
Shengyu Fu - Redmond WA, US
Neelakantan Sundaresan - Bellevue WA, US
Shao Kun Deng - Bellevue WA, US

International Classification:

G06F 8/33
G06N 3/08
G06N 5/04
G06F 17/18
G06F 17/16
G06F 16/901

Abstract:

A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.