View source for 18535473. Augmentation of Code Completion and Code Synthesis with Semantic Checking simplified abstract (GOOGLE LLC)

=Augmentation of Code Completion and Code Synthesis with Semantic Checking=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Maxim Tabachnyk of Munich (DE)|Maxim Tabachnyk of Munich (DE)]][[Category:Maxim Tabachnyk of Munich (DE)]]

[[:Category:Yurun Shen of Mountain View CA (US)|Yurun Shen of Mountain View CA (US)]][[Category:Yurun Shen of Mountain View CA (US)]]

[[:Category:Stoyan Stefanov Nikolov of Planegg (DE)|Stoyan Stefanov Nikolov of Planegg (DE)]][[Category:Stoyan Stefanov Nikolov of Planegg (DE)]]

[[:Category:Stanislav Pyatykh of Unterhaching (DE)|Stanislav Pyatykh of Unterhaching (DE)]][[Category:Stanislav Pyatykh of Unterhaching (DE)]]

[[:Category:Ksenia Korovina of Mountain View CA (US)|Ksenia Korovina of Mountain View CA (US)]][[Category:Ksenia Korovina of Mountain View CA (US)]]

[[:Category:Evgeny Gryaznov of Mountain View CA (US)|Evgeny Gryaznov of Mountain View CA (US)]][[Category:Evgeny Gryaznov of Mountain View CA (US)]]

[[:Category:Erik Grabljevec of Mountain View CA (US)|Erik Grabljevec of Mountain View CA (US)]][[Category:Erik Grabljevec of Mountain View CA (US)]]

==Augmentation of Code Completion and Code Synthesis with Semantic Checking - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18535473 titled 'Augmentation of Code Completion and Code Synthesis with Semantic Checking

==Simplified Explanation==

The abstract describes a method for providing autofill suggestions in a development environment by using machine learning models and rule-based semantic checkers.

* Obtaining user input representing source code generated within a development environment.
* Determining autofill suggestions based on the user input using a machine learning model.
* Checking the semantic correctness of the autofill suggestions using a rule-based semantic checker.
* Transmitting the autofill suggestion for display when it is semantically correct.

== Potential Applications ==
This technology could be applied in software development tools to assist programmers in writing code more efficiently and accurately.

== Problems Solved ==
1. Helps programmers save time by providing autofill suggestions for completing code.
2. Ensures the correctness of the autofill suggestions by checking their semantic accuracy.

== Benefits ==
1. Increases productivity for developers by speeding up the coding process.
2. Reduces the likelihood of errors in the code by providing accurate autofill suggestions.

== Potential Commercial Applications ==
Enhancing integrated development environments (IDEs) with advanced autofill features for software development teams.

== Possible Prior Art ==
One possible prior art could be the use of autocomplete features in text editors or IDEs, but the specific combination of machine learning models and rule-based semantic checkers for autofill suggestions may be novel.

== Unanswered Questions ==
=== How does the machine learning model determine the autofill suggestions based on user input? ===
The exact process and algorithms used by the machine learning model to generate autofill suggestions could provide more insight into the accuracy and relevance of the suggestions.

=== What programming languages and code bases are supported by the rule-based semantic checker? ===
Understanding the scope and compatibility of the rule-based semantic checker with different programming languages and code bases could help assess the versatility of the technology.


==Original Abstract Submitted==

A method for providing autofill suggestions in a development environment includes obtaining, from a user interface executing on a user device, a user input representing source code generated within a development environment. The source code is created using a particular programming language and a programming code base. The method further includes determining, using a machine learning model, at least one autofill suggestion based on the user input, the autofill suggestion continuing the source code represented by the user input. The method further includes determining, using a rule-based semantic checker configured for the particular programming language, whether the autofill suggestion is semantically correct based on the development environment and the programming code base. The method also includes, when the autofill suggestion is semantically correct, transmitting the autofill suggestion for display on the user interface of the user device.



[[Category:G06F8/33]]