IP Library Granted Patent US 12,216,674
Granted Patent B2
US 12,216,674 · App. 18/178,653 · Granted Feb 4, 2025

Systems and methods for writing feedback using an artificial intelligence engine

Inventors: Aleksey Aleksandrovich Sokolov (Snoqualmie, WA); Utkarsh Garg (Bellevue, WA); Siqing Chen (Bellevue, WA); Warren Anthony Aldred (Redmond, WA); Saket Kumar (Buckley, WA); Cheng Yang (Chengdu, CN); Bhavuk Jain (Redmond, WA); Mahaveer Bhavarlal Kothari (Redmond, WA); Alyssa Rachel Mayo (New Rochelle, NY); Tashfeen Ahmed (Dublin, IE); Zhang Li (Seattle, WA); Olivier Michel Nicolas Gauthier (Duvall, WA); Christine Lauren Mayer (Seattle, WA); Jesse Alexander Freitas (Seattle, WA)
Assignee: Microsoft Technology Licensing, LLC
G06F16/248G06F16/245G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,216,674
App. No.
18/178,653
Granted
Feb 4, 2025
Kind
B2
Abstract

A data processing system includes: a processor; a memory containing programming instructions for execution by the processor; and a network interface for communicating with an Artificial Intelligence (AI) engine. The programming instructions include an application for generating written content, the application having a function to generate and submit a structured query regarding the written content to the AI engine to generate feedback on an assessed quality of the written content, the structured query structured to prompt for feedback in a variety of specified categories for the written content. The application further includes a user interface to display the feedback on the written content and provide an option to a user to implement the feedback to revise the written content.

Claims (33)

1. A data processing system comprising:

a processor;

a memory containing programming instructions for execution by the processor; and

a network interface for communicating with an Artificial Intelligence (AI) engine;

the programming instructions comprising an application with a user interface allowing the user to operate tools for generating written content,

the application having a function to generate and submit a structured query regarding the written content to the AI engine to generate feedback on an assessed quality of the written content, wherein the application is to determine a number of document parameters relevant to the written content, the document parameters being incorporated into the structured query by the application, the structured query being structured to prompt the AI engine to provide feedback in a variety of specified categories of assessed quality of the written content, the feedback comprising a number of recommendations for editing the written content;

the application further comprising a user interface to display the feedback on the assessed quality of the written content and provide a tool with which a user has an option to implement the feedback to revise the written content.

2. The data processing system of claim 1 , wherein the programming instructions comprise an add-in or plug-in comprising the function to generate and submit the structured query.

3. The data processing system of claim 1 , wherein a structure of the query specifies categories of feedback to be returned by the AI engine.

4. The data processing system of claim 1 , wherein a structure of the query specifies a prompt to critique the written content and, for each critique, to provide (1) a title, (2) a description of the critique (2a) respecting a specific tone and (2b) respecting a specific format, (3) an example of the critique in the document and (4) a suggested rewrite.

5. The data processing system of claim 1 , wherein the user interface comprises a prompt to the user to invoke the function to generate feedback on an assessed quality of the written content.

6. The data processing system of claim 1 , wherein the user interface comprises a tool for designating a portion of the written content on which to generate the feedback.

7. The data processing system of claim 1 , wherein the user interface divides the feedback from the AI engine among a plurality of cards.

8. The data processing system of claim 1 , wherein the feedback based on the structure of the query comprises at least one rewritten portion of the written content, the user interface further comprising an option to automatically replace an original portion of the written content with the rewritten portion from the feedback.

9. The data processing system of claim 1 , wherein the user interface comprises a tool for the user to enter or adjust the document parameters.

10. The data processing system of claim 1 , wherein the user interface further comprises a tool that interacts on a canvas of the written content to highlight text for which feedback has been received based on the structured query, the tool comprising options to implement or discard the feedback on the highlighted text.

11. The data processing system of claim 1 , the user interface further comprising an option to request that an additional query be sent to the AI engine for an alternative to any of the number of recommendations.

12. The data processing system of claim 1 , wherein the user interface comprises options for rating a recommendation on the written content contained in the feedback from the AI engine.

13. A non-transitory computer-readable medium comprising programming instructions that, when executed by a processor, cause the processor to:

generate a structured query for an Artificial Intelligence (AI) engine regarding designated written content, wherein the designated written content is designated in an application with a user interface allowing the user to operate tools for generating written content, and the application is configured to determine a number of document parameters relevant to the written content, the document parameters being incorporated into the structured query by the application, the structured query to the AI engine to generate feedback on an assessed quality of the written content, the structured query being structured to prompt the AI engine to provide feedback in a variety of specified categories of assessed quality of the written content, the feedback comprising a number of recommendations for editing the written content;

submit the query to the AI engine via a network interface;

receive the feedback on the assessed quality of the written content from the AI engine via the network interface; and

invoke a user interface of the application to display the feedback on the written content and provide an option to a user to implement the feedback to revise the written content, wherein the user interface is to display the feedback on the assessed quality of the written content and provide a tool with which a user has an option to implement the feedback to revise the written content.

14. The non-transitory computer-readable medium of claim 13 , wherein the programming instructions comprise an add-in or plug-in for the application, the add-in or plug-in comprising a function to generate and submit the structured query.

15. The non-transitory computer-readable medium of claim 13 , wherein a structure of the query specifies a prompt to critique the written content and, for each critique, to provide (1) a title, (2) a description of the critique (2a) respecting a specific tone and (2b) respecting a specific format, (3) an example of the critique in the document and (4) a suggested rewrite.

16. The non-transitory computer-readable medium of claim 13 , wherein the feedback based on the structure of the query comprises at least one rewritten portion of the written content, the user interface further comprising an option to automatically replace an original portion of the written content with the rewritten portion from the feedback.

17. A computer-implemented method of providing technical writing assistance to a user operating an application to generate written content by providing feedback on the written content from an Artificial Intelligence (AI) engine, the method comprising:

generating a structured query for an Artificial Intelligence (AI) engine regarding designated written content, wherein the designated written content is designated in an application with a user interface allowing the user to operate tools for generating written content, and the application is configured to determine a number of document parameters relevant to the written content, the document parameters being incorporated into the structured query by the application, the structured query to the AI engine to generate feedback on an assessed quality of the written content, the structured query being structured to prompt the AI engine to provide feedback in a variety of specified categories of assessed quality of the written content, the feedback comprising a number of recommendations for editing the written content;

submitting the query to the AI engine via a network interface;

receiving the feedback on the assessed quality of the written content from the AI engine via the network interface; and

invoking a user interface of the application to display the feedback on the written content, wherein the user interface is to display the feedback on the assessed quality of the written content and provide a tool with which a user has an option to implement the feedback to revise the written content.

18. The method of claim 17 , further comprising augmenting the application with an add-in or plug-in comprising programming for generating and submitting the structured query.

19. The method of claim 17 , wherein the structured query is in Natural Language and a structure of the query specifies a prompt to critique the written content and, for each critique, to provide (1) a title, (2) a description of the critique (2a) respecting a specific tone and (2b) respecting a specific format, (3) an example of the critique in the document and (4) a suggested rewrite.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 6, 2023
From: SOKOLOV, ALEKSEY ALEKSANDROVICH; GARG, UTKARSH; CHEN, SIQING; ALDRED, WARREN ANTHONY; KUMAR, SAKET; YANG, CHENG; JAIN, BHAVUK; KOTHARI, MAHAVEER BHAVARLAL; MAYO, ALYSSA RACHEL; AHMED, TASHFEEN; LI, ZHANG; GAUTHIER, OLIVIER MICHEL NICOLAS; MAYER, CHRISTINE LAUREN; FREITAS, JESSE ALEXANDER
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 062957/0474 →
Continuity (1)
Related Publication 20240303247A1 · Sep 12, 2024
References Cited (13)
US 20140032471A1 · Reddy · 2014 [cited by examiner]
US 20170147945A1 · Henderson · 2017 [cited by examiner]
US 20170357910A1 · Sommer · 2017 [cited by examiner]
US 20180174019A1 · Henderson · 2018 [cited by examiner]
US 20210397793A1 · Li et al. · 2021 [cited by applicant]
US 20220051098A1 · McCarthy · 2022 [cited by examiner]
US 20230072925A1 · Ross · 2023 [cited by examiner]
“Application as filed in U.S. Appl. No. 17/583,909”, Mailed Date: Jan. 25, 2022, 53 Pages. [cited by applicant]
International Search Report and Written Opinion received for PCT Application No. PCT/US2024/017784, Jul. 30, 2024, 10 pages. [cited by applicant]
“Plug-in (computing)—Wikipedia,” Retrieved from the Internet: URL: https://en.wikipedia.org/w/index.phptitle=Plugin_(computing)&oldid=1135751075, Jan. 26, 2023, 03 Pages. [cited by applicant]
How, Tech, “How ChatGPT Can Improve Your Writing: A Hands-On Demonstration,” Retrieved from the Internet: URL https://www.youtube.com/watch?v=ISpT87IdFoE, Jan. 15, 2023, 02 Pages. [cited by applicant]
Jenn, Jie “Create A Professional Grammar Check GUI App with Open AI GPT API and Python (Full Tutorial),” Retrieved from the Internet: URL: https://www.youtube.com/watch?v=H0tADg4RodQ, Feb. 6, 2023, 02 Pages. [cited by applicant]
Stratvert, Kevin, “How to use Microsoft Editor,” Retrieved from the Internet: URL: https://www.youtube.com/watchv=BHRKXDmv9el, Aug. 19, 2021, 02 Pages. [cited by applicant]
Cited By (5)
US 12,493,740 US 12,541,638 US 12,566,916 US 12,632,669 US 12,657,198