US Patent Application 17721730. Editing Files using a Pattern-Completion Engine simplified abstract

From WikiPatents
Jump to navigation Jump to search

Editing Files using a Pattern-Completion Engine

Organization Name

Microsoft Technology Licensing, LLC


Inventor(s)

Christian Alexander Cosgrove of Stanford CA (US)


Saurabh Kumar Tiwary of Bellevue WA (US)


Editing Files using a Pattern-Completion Engine - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 17721730 Titled 'Editing Files using a Pattern-Completion Engine'

Simplified Explanation

This abstract describes a technique for helping users edit files. The technique involves providing the user with information about the current context, including their editing objective and a selected portion of the file. The technique then uses a pattern-completion engine to generate suggestions for edits based on this information. The engine uses a machine-trained model that has been trained on revision history data. The model is tested to ensure that the suggested edits are effective, meet performance standards, and align with the user's editing goals.


Original Abstract Submitted

A technique is described herein for assisting a user in editing a file. The technique involves producing current context information that includes an input message and selected file content. The input message describes a user's editing objective, while the selected file content describes a portion of the file to which the editing objective is to be applied. The technique then requests a pattern-completion engine to generate edit information based on the current context information. The edit information describes one or more changes to the selected file content that satisfy the objective of the user. The pattern-completion engine uses a machine-trained autoregressive text-completion model that is trained on revision history information. The model can be trained in a process that incorporates various tests to ensure that the edit information that is generated works as expected, satisfies various performance metrics, and fulfills the editing objectives of the user.