Learning session-specific code recommendations for editing code files
AssigneeAmazon Technologies, Inc.
InventorsWillem Conradie Visser, Sengamedu Hanumantha Rao Srinivasan
Life of this patent
Estimating the term…
Abstract
Session-specific edit recommendations may be made for editing a code file. After a code editing session is started, code file edits may be captured. A machine learning technique may be applied to learn the code edits and recommend alternative code portions for portions of the code file during the code editing session. The recommendations may be provided and accepted, or not, via an interface of a code editor application.
Claims20
A system, comprising:
- at least one processor;
- and
- a memory, storing program instructions that when executed by the at least one processor, cause the at least one processor to implement an integrated development environment, the integrated development environment configured to:
- capture one or more edits to a code file received via an interface of the integrated development environment during an editing session;
- update an artifact used by a machine learning technique to include the captured one or more edits;
- after the update to the artifact:
- apply, during the code editing session, the machine learning technique to identify one or more portions of the code file to replace with respective alternative code portions, wherein the application of the machine learning technique:
- recognizes the one or more portions according to the captured one or more edits;
- and
- determines corresponding ones of the captured one or more edits as providing the respective alternative code portions;
- and
- display, via the interface, the respective alternative code portions as recommendations to replace the one or more portions of the code file.
A method, comprising:
- identifying, by a code editor application during an editing session, one or more portions of a code file to replace with respective alternative code portions, wherein the identifying comprises:
- applying a machine learning technique associated with the editing session that:
- recognizes the one or more portions according to one or more previous edits made to the code file during the editing session;
- and
- determines corresponding ones of the one or more previous edits as the respective alternative code portions;
- and
- providing, via an interface of the code editor application, the respective alternative code portions as recommendations to replace the one or more portions of the code file.
One or more non-transitory, computer-readable storage media, storing program instructions that when executed on or across one or more computing devices cause the one or more computing devices to implement:
- identifying, by a code editor application during an editing session, one or more portions of a code file to replace with respective alternative code portions, wherein, in identifying the one or more portions of the code file, the program instructions cause the one or more computing devices to implement:
- applying a machine learning technique associated with the editing session that:
- recognizes the one or more portions according to one or more previous edits made to the code file during the editing session;
- and
- determines corresponding ones of the one or more previous edits as the respective alternative code portions;
- and
- displaying, via an interface of the code editor application, the respective alternative code portions as recommendations to replace the one or more portions of the code file.
Dependencies are inferred from the claim text.