IP Library › Granted Patent US 12,505,283
Granted Patent B2
US 12,505,283 · App. 18/995,049 · Granted Dec 23, 2025

Computer-implemented methods and systems for dynamic prompt generation and integration with large language models for document revision

Inventor: Robert Plotkin (Manalapan, NJ)
Assignee: Quabbin Patent Holdings, Inc.
G06F40/166G06F3/0482G06F3/0486G06F40/284G06F40/40
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 12,505,283
App. No.
18/995,049
Granted
Dec 23, 2025
Kind
B2
Abstract

Computer-implemented methods and systems interface with a language model (e.g., a Large Language Model (LLM)) to assist in document revision. The methods and systems allow text to be selected within a document and an action definition to be selected from an action definition library. The text and/or the action definition may be selected using a graphical user interface (GUI). An action defined by the selected action definition is applied to the selected text to generate text. For example, the selected action definition may include a prompt, and the prompt may be combined with the selected text to generate a combined prompt. The combined prompt may be provided as an input to the LLM, which may generate the generated text. The generated text may be integrated into the document.

Claims (52)

1 . A method performed by at least one computer processor executing computer program instructions stored on at least one non-transitory computer-readable medium, the method comprising:

(A) receiving, from a user, via a prompt editor of a graphical user interface (GUI), a plurality of initial prompt definition inputs;

(B) creating plurality of initial prompts from the plurality of initial prompt definition inputs, wherein each of the plurality of initial prompts includes content from a corresponding one of the initial prompt definition inputs;

(C) receiving, via the GUI, input from the user selecting text within a document, wherein receiving input from the user selecting text within the document comprises receiving input from the user selecting a contiguous block of text within the document;

(D) receiving, via the GUI, input from the user selecting a particular initial prompt from among the plurality of initial prompts;

(E) generating, based on the selected text and the particular initial prompt, a processed prompt;

(F) providing the processed prompt to a language model to generate output; and

(G) updating the document based on the output.

2 . The method of claim 1 , wherein receiving input from the user selecting text within the document comprises receiving input from the user dragging across text within a manifestation of the document in the GUI.

3 . The method of claim 1 , wherein receiving input from the user selecting the particular initial prompt comprises receiving input from the user selecting an identifier of the particular initial prompt from a list of initial prompt identifiers manifested in the GUI.

4 . The method of claim 1 , wherein receiving input from the user selecting the particular initial prompt comprises receiving input from the user selecting a manifestation of an action definition from a contextual menu.

5 . The method of claim 1 , wherein the particular initial prompt comprises a simple text prompt containing no dynamic content.

6 . The method of claim 1 , wherein the particular initial prompt comprises a tokenized prompt, the tokenized prompt comprising at least one token acting as a placeholder for dynamic content.

7 . The method of claim 1 , wherein the particular initial prompt comprises a compound prompt comprising multiple component prompts that differ from each other.

8 . The method of claim 7 , wherein (F) comprises:

(F) (1) performing (F) for each of the compound prompt's multiple component prompts to generate a plurality of outputs;

(F) (2) manifesting the plurality of outputs to the user; and

(F) (3) receiving, via the GUI, input from the user selecting one of the plurality of outputs.

9 . The method of claim 7 , wherein (F) comprises:

(F) (1) performing step (F) for a first component prompt of the compound prompt to generate a first output; and

(F) (2) performing step (F) for a second component prompt of the compound prompt, using the first output as an input to the language model, to generate second output.

10 . The method of claim 1 , wherein the particular initial prompt comprises a scripted prompt written in a scripting language.

11 . The method of claim 1 , wherein generating the processed prompt comprises concatenating the particular initial prompt with the selected text.

12 . The method of claim 1 , wherein the particular initial prompt comprises a tokenized prompt containing a token, and wherein generating the processed prompt comprises:

(E) (1) obtaining a value for the token; and

(E) (2) replacing the token with the value.

13 . The method of claim 12 , wherein obtaining the value for the token comprises using a trained model to generate the value.

14 . The method of claim 13 , wherein using the trained model to generate the value comprises using the language model to generate the value.

15 . The method of claim 1 , wherein generating the processed prompt comprises:

(E) (1) providing the selected text and the particular initial prompt as inputs to the language model; and

(E) (2) receiving the processed prompt as output from the language model.

16 . The method of claim 1 , wherein the language model comprises a large language model (LLM).

17 . The method of claim 1 , wherein providing the processed prompt to the language model comprises:

(F) (1) receiving, from the user, language model selection input selecting the language model from a plurality of language models; and

(F) (2) providing the processed prompt to the language model.

18 . The method of claim 1 , wherein updating the document based on the output comprises inserting the output into the document immediately after the selected text.

19 . The method of claim 1 , wherein updating the document based on the output comprises:

(G) (1) receiving, via the GUI, input from the user specifying a location in the document other than a location of the selected text; and

(G) (2) inserting the output into the document at the location specified by the user.

20 . The method of claim 1 , wherein updating the document based on the output comprises replacing the selected text in the document with the output.

21 . The method of claim 1 , wherein updating the document based on the output comprises:

(G) (1) manifesting a preview of the document updated with the output to the user via the GUI;

(G) (2) receiving, via the GUI, input from the user accepting the preview; and

(G) (3) updating the document in response to receiving the input from the user accepting the preview.

22 . A system comprising at least one non-transitory computer-readable medium having computer program instructions stored thereon, the computer program instructions being executable by at least one computer process to perform a method, the method comprising:

(A) receiving, from a user, via a prompt editor of a graphical user interface (GUI), a plurality of initial prompt definition inputs;

(B) creating a plurality of initial prompts from the plurality of initial prompt definition inputs, wherein each of the plurality of initial prompts includes content from a corresponding one of the initial prompt definition inputs;

(C) receiving, via the GUI, input from the user selecting text within a document, wherein receiving input from the user selecting text within the document comprises receiving input from the user selecting a contiguous block of text within the document;

(D) receiving, via the GUI, input from the user selecting a particular initial prompt from among the plurality of initial prompts;

(E) generating, based on the selected text and the particular initial prompt, a processed prompt;

(F) providing the processed prompt to a language model to generate output; and

(G) updating the document based on the output.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 4, 2025
From: PLOTKIN, ROBERT
To: QUABBIN PATENT HOLDINGS, INC.
Reel/Frame 070389/0957 →
Continuity (2)
Provisional Application 63588835 · Oct 9, 2023
Related Publication 20250258994A1 · Aug 14, 2025
References Cited (47)
US 5493606A · Osder et al. · 1996 [cited by examiner]
US 20060203980A1 · Starkie · 2006 [cited by applicant]
US 20140379615A1 · Brigham et al. · 2014 [cited by examiner]
US 20200153687A1 · Ayyagari et al. · 2020 [cited by examiner]
US 20210042662A1 · Pu et al. · 2021 [cited by examiner]
US 20220229832A1 · Li et al. · 2022 [cited by examiner]
US 20230075884A1 · Jakobsson · 2023 [cited by applicant]
US 20230316006A1 · Tunstall-Pedoe et al. · 2023 [cited by examiner]
US 20240112394A1 · Neal · 2024 [cited by applicant]
US 20240338860A1 · Trzyna · 2024 [cited by applicant]
US 20240419907A1 · Laprise · 2024 [cited by applicant]
US 20240420418A1 · Wu · 2024 [cited by applicant]
US 20250007870A1 · Kim et al. · 2025 [cited by examiner]
US 20250013438A1 · G00dman et al. · 2025 [cited by examiner]
US 20250118022A1 · Fitzmaurice et al. · 2025 [cited by examiner]
CN 116700839A · 2023 [cited by applicant]
CN 116795973A · 2023 [cited by applicant]
CN 117313746A · 2023 [cited by applicant]
CN 117409109A · 2024 [cited by applicant]
EP 1006452A2 · 2000 [cited by applicant]
Office Action dated May 8, 2025 for U.S. Appl. No. 19/054,800 (pp. 1-12). [cited by applicant]
Cohen, Reuven, “The Future of AI Infused Documents: The Intelligent Document Format,” Linkedln, Feb. 5, 2024. 2 pages. [cited by applicant]
Openai, “A New Way of Working With ChatGPT to Write and Code,” Introducing Canvas, Oct. 3, 2024, 8 pages. openai.com/index/introducing-canvas/. [cited by applicant]
“How do I add a Ghostwriter prompt?” Cloze Help Center, 9 pages, printed Oct. 10, 2023, URL: htpps://help.cloze.com/article/2680-how-do-i-add-a-ghostwriter-prompt. [cited by applicant]
“Word GPT Plus—a useful add-in to use chatGPT in Microsoft Word,” Apr. 27, 2023, 3 pages. [cited by applicant]
AI-Writer.com, “Use AI to your advantage, without sacrificing on quality,” 2023, Product Guide, 22 pages. [cited by applicant]
Coyer, Cassandre, “LexisNexis Brings Lexis Create to U.S., Announces New Gen AI Capabilities Ahead,” Aug. 2, 2023, 2 pages. URL: https://www.law.com/legaltechnews/2023/08/02/lexisnexis-brings-lexis-create-to-u-s-announc… [cited by applicant]
Coyer, Cassandre, “LexisNexis Publicly Releases Generative AI-Powered Lexis+AI, With New Functionalities,” Oct. 25, 2023, 2 pages. URL: https://www.law.com/legaltechnews/2023/10/25/lexisnexis-publicly-releases-generativ… [cited by applicant]
Dipshan, Rhys, “LexisNexis Expands Generative AI Offerings With Lexis Snapshot and Lexis Create Integration,” Nov. 14, 2023, 2 pages. URL: https://www.law.com/legaltechnews/2023/11/14/lexisnexis-expands-generative-ai-of… [cited by applicant]
Gemini, “Supercharge your creativity and productivity,” Release updates, 2024, 12 pages. URL: gemini.google.com/updates. [cited by applicant]
Ghostwriter-AI, Solving insight problems with clarity, simplicity and innovation, “Ghostwriter Add-ins for Microsoft Office,” printed Oct. 10, 2023, 30 pages. URL: https://www.ghostwriter-ai.com/. [cited by applicant]
Guerra, Marci, “Chat GPT for Microsoft Word: A Guide to Integration and Usage,” Brandalytics, Apr. 14, 2023. 11 pages. [cited by applicant]
International Search Report and Written Opinion issued in App. No. PCT/US2024/050403, dated Jan. 15, 2025, 10 pages. [cited by applicant]
Jasper, “Meet Jasper. On-brand AI content wherever you create.” Product Guide, printed Oct. 1, 2023, 49 pages. [cited by applicant]
Kowalczyk, Mikolaj, “A Step-by-step Guide to Prompt Engineering: Best Practices, Challenges, and Examples,” printed Oct. 1, 2023, 16 pages. [cited by applicant]
Lago, Juan Pablo, “Guiding LLM Behavior: The Art of Prompt Engineering,” Aug. 15, 2023, 13 pages. URL: https://blog.marvik.ai/2023/08/15/prompt-engineering-guide/. [cited by applicant]
Li, Abner, “Gemini now lets you tune and modify responses with a prompt,” Mar. 6, 2024, 3 pages. URL: 9to5google.com/2024/03/06/gemini-modify-tune-response/. [cited by applicant]
OpenAI, Blog, “New models and developer products announced at DevDay,” GPT-4 Turbo with 128K context and lower prices, the new Assistants API, GPT-4 Turbo with Vision, DALL-E 3 API, and more. Nov. 6, 2023 announcements,… [cited by applicant]
Peppercontent “Peppertype just got better!” Introducing the all-new AI-powered Content Marketing Platform, printed Oct. 1, 2023, 10 pages. [cited by applicant]
Sha, Arjun, “How to Integrate ChatGPT Into Microsoft Word,” last updated Jun. 19, 2023. 17 pages. URL: https://beebom.com/how-add-chatgpt-microsoft-word/. [cited by applicant]
Shi, F et al. “Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models,” Jun. 6, 2023, 25 pages. [cited by applicant]
Spataro, Jared, “Introducing Microsoft 365 Copilot—your copilot for work,” Mar. 16, 2023, CVP Modern Work & Business Applications, Official Microsoft Blog, 14 pages. [cited by applicant]
Stanojevic, Milan, “How to Integrate ChatGPT With Word [Quickest Ways],” To use ChatGPT in Word, you need to rely on third-party add-ons, Windowsreport, updated Oct. 4, 2023, 19 pages. [cited by applicant]
What's New in Copilot, techcommunity.microsoft.com/blog/microsoft365copilotblog/whats-new-in-copilot--august-2024/4226565, Aug. 30, 2024, 5 pages. [cited by applicant]
Woodie, Alex, “DSPy Puts 'Programming Over Prompting' in AI Model Development”, Datanami, Aug. 25, 2023. 4 pages. [cited by applicant]
www.microsoft.com, “Introducing Microsoft 365 Copilot13 your copilot for work.” 2023, 12 pages. [cited by applicant]
Yeh, C. et al. “GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency,” Feb. 13, 2024, 29 pages. [cited by applicant]