IP Library Granted Patent US 12,437,022
Granted Patent B1
US 12,437,022 · App. 18/664,598 · Granted Oct 7, 2025

Dynamic generation of work requests

Inventors: Darryl Gehly (Temple, NH); Carolyn Byrne (Rockwood, ME); Samuel Gehly (Temple, NH); Nathanael Newby-Kew (Medford, MA); Anna Nobile (Austin, TX); Sonny Sharp (Highland Park, IL); Timothy Tresch (Bethal Park, PA); Andrew Wheeler (Cohassett, MA)
Assignee: Skyword, Inc.
G06F16/957G06F16/9538
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 12,437,022
App. No.
18/664,598
Granted
Oct 7, 2025
Kind
B1
Abstract

Aspects described herein generally relate to improving search engine optimization (SEO) by improving a process for selecting keywords for search engine optimization, constructing work requests based on selected keywords and output from a first and second large learning model (LLM), and selecting potential contributors to draft articles based on the work requests and prior drafting experience. More specifically, aspects provide for faster construction of work requests and selection of potential qualified contributors. Aspects further provide for improved ability to track SEO improvements for selected keywords.

Claims (93)

1. A computer-implemented method for dynamically generating work requests for search engine optimization (SEO), comprising:

receiving a target website parameter, indicating a target website for SEO, and one or more prompt parameters;

configuring a first keyword query with one or more keyword query parameters;

initiating the first keyword query;

displaying, via a user interface, a result of the first keyword query, wherein the result comprises:

a keyword, and

a first rank, wherein the first rank indicates how highly the target website is displayed in a search engine results page for the keyword;

receiving, via the user interface, a selection of a first keyword;

constructing, based on the first keyword and one or more of the prompt parameters, a first prompt and a second prompt, wherein each prompt comprises an input statement for a large language model (LLM);

receiving, from a first LLM, a first output corresponding to the first prompt;

receiving, from a second LLM, a second output corresponding to the second prompt;

constructing a first work request based on the first output and the second output, wherein the first work request is associated with first keyword;

identifying one or more contributor keywords, wherein a contributor keyword indicates a topic associated with the first work request;

selecting, based on the one or more contributor keywords, one or more contributors, wherein a contributor is associated with at least one contributor keyword;

sending the first work request to the one or more contributors;

receiving one or more bids from the one or more contributors, wherein a bid is associated with a contributor and comprises an offer to draft an article based on the first work request;

selecting a first bid; and

assigning the first work request to a first contributor associated with the first bid.

2. The method of claim 1 , wherein the first output comprises instructions for a contributor to draft an article to improve a rank of the target website on a search engine results page for the first keyword.

3. The method of claim 1 , wherein the second output comprises an outline for an article to improve a rank of the target website on a search engine results page for the first keyword.

4. The method of claim 1 , wherein the one or more keyword query parameters comprise at least one of:

one or more comparison website parameters, wherein a comparison website is a website different from the target website;

a search type parameter; and

a search intent parameter, indicating a type of information a consumer intends to learn when searching for a keyword.

5. The method of claim 4 , wherein the result of the first keyword query further comprises:

a second rank, wherein the second rank indicates how highly a comparison website is displayed in a search engine results page for the keyword.

6. The method of claim 1 , wherein a contributor is associated with at least one contributor keyword based on:

identifying, based on one or more articles by a contributor, one or more contributor keywords associated with the one or more articles.

7. The method of claim 1 , herein a result further comprises:

a search frequency, wherein the search frequency of the keyword is further based on a number of times that the keyword was searched over a given period of time.

8. The method of claim 1 , wherein the first rank is further based on:

how highly the target website is displayed in the search engine results page for the keyword over a period of time.

9. A computing device configured to dynamically generate work requests for search engine optimization (SEO), the computing device comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the computing device to:

receive a target website parameter, indicating a target website for SEO, and one or more prompt parameters;

configure a first keyword query with one or more keyword query parameters;

initiate the first keyword query;

display, via a user interface, a result of the first keyword query, wherein the result comprises:

a keyword, and

a first rank, wherein the first rank indicates how highly the target website is displayed in a search engine results page for the keyword;

receive, via the user interface, a selection of a first keyword;

construct, based on the first keyword and one or more of the prompt parameters, a first prompt and a second prompt, wherein a prompt comprises an input statement for a large language model (LLM);

receive, from a first LLM, a first output corresponding to the first prompt;

receive, from a second LLM, a second output corresponding to the second prompt;

construct a first work request based on the first output and the second output, wherein the first work request is associated with first keyword;

identify one or more contributor keywords, wherein a contributor keyword indicates a topic associated with the first work request;

select, based on the one or more contributor keywords, one or more contributors, wherein a contributor is associated with at least one contributor keyword;

send the first work request to the one or more contributors;

receive one or more bids from the one or more contributors, wherein a bid is associated with a contributor and comprises an offer to draft an article based on the first work request;

select a first bid; and

assign the first work request to a first contributor associated with the first bid.

10. The computing device of claim 9 , wherein the first output comprises instructions for a contributor to draft an article to improve a rank of the target website on a search engine results page for the first keyword.

11. The computing device of claim 1 , wherein the one or more keyword query parameters comprise at least one of:

one or more comparison website parameters, wherein a comparison website is a website different from the target website;

a search type parameter; and

a search intent parameter, indicating a type of information a consumer intends to learn when searching for a keyword.

12. The computing device of claim 11 , wherein the result of the first keyword query further comprises:

a second rank, wherein the second rank indicates how highly a comparison website is displayed in a search engine results page for the keyword.

13. The computing device of claim 9 , wherein a result further comprises:

a search frequency, wherein the search frequency of the keyword is further based on a number of times that the keyword was searched over a given period of time.

14. The computing device of claim 9 , wherein the first rank is further based on:

how highly the target website is displayed in the search engine results page for the keyword over a period of time.

15. The computing device of claim 9 , wherein a contributor is associated with at least one contributor keyword based on:

identify, based on one or more articles by the contributor, one or more contributor keywords associated with the one or more articles.

16. One or more non-transitory computer-readable media storing instructions for dynamically generating work requests for search engine optimization (SEO) that, when executed by one or more processors, cause a computing device to perform steps comprising:

receiving a target website parameter, indicating a target website for SEO, and one or more prompt parameters;

configuring a first keyword query with one or more keyword query parameters;

initiating the first keyword query;

displaying, via a user interface, a result of the first keyword query, wherein a result comprises:

a keyword, and

a first rank, wherein the first rank indicates how highly the target website is displayed in a search engine results page for the keyword;

receiving, via the user interface, a selection of a first keyword;

constructing, based on the first keyword and one or more of the prompt parameters, a first prompt and a second prompt, wherein a prompt is an input statement for a large language model (LLM);

receiving, from a first LLM, a first output corresponding to the first prompt;

receiving, from a second LLM, a second output corresponding to the second prompt;

constructing a first work request based on the first output and the second output, wherein the first work request is associated with first keyword;

identifying one or more contributor keywords, wherein a contributor keyword indicates a topic associated with the first work request;

selecting, based on the one or more contributor keywords, one or more contributors, wherein a contributor is associated with at least one contributor keyword;

sending the first work request to the one or more contributors;

receiving one or more bids from the one or more contributors, wherein a bid is associated with a contributor and comprises an offer to draft an article based on the first work request;

selecting a first bid; and

assigning the first work request to a first contributor associated with the first bid.

17. The one or more non-transitory computer-readable media storing instructions of claim 16 , wherein the one or more keyword query parameters comprise at least one of:

one or more comparison website parameters, wherein a comparison website is a website different from the target website;

a search type parameter; and

a search intent parameter, indicating a type of information a consumer intends to learn when searching for a keyword.

18. The one or more non-transitory computer-readable media storing instructions of claim 17 , wherein the result of the first keyword query further comprise:

a second rank, wherein the second rank indicates how highly a comparison website is displayed in a search engine results page for the keyword.

19. The one or more non-transitory computer-readable media storing instructions of claim 16 , wherein a contributor is associated with at least one contributor keyword based on:

identifying, based on one or more articles by the contributor, one or more contributor keywords associated with the one or more articles.

20. The one or more non-transitory computer-readable media storing instructions of claim 16 , wherein a result further comprises:

a search frequency, wherein the search frequency of the keyword is further based on a number of times that the keyword was searched over a given period of time.

Assignments (2)
SECURITY INTEREST Recorded Dec 11, 2024
From: SKYWORD INC.
To: HERCULES CAPITAL, INC.
Reel/Frame 069554/0205 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 29, 2024
From: SHARP, SONNY; NOBILE, ANNA; GEHLY, DARRYL; GEHLY, SAMUEL; TRESCH, TIMOTHY; BYRNE, CAROLYN; WHEELER, ANDREW; NEWBY-KEW, NATHANAEL
To: SKYWORD INC.
Reel/Frame 068108/0656 →
References Cited (25)
US 20080243608A1 · Chatow · 2008 [cited by examiner]
US 20090063265A1 · Nomula · 2009 [cited by examiner]
US 20210200943A1 · Aviyam · 2021 [cited by examiner]
US 20240273306A1 · Somaiya · 2024 [cited by examiner]
US 20240303437A1 · Kraus · 2024 [cited by examiner]
US 20240330383A1 · Ros · 2024 [cited by examiner]
US 20240330579A1 · Saxena · 2024 [cited by examiner]
US 20240362903A1 · Palatnik de Sousa · 2024 [cited by examiner]
Smith, Shelly, “4 Types of Search Intent,” Medium, Oct. 19, 2023, 11 pages, <https://medium.com/@exec.shellybeanllc/4-types-of-search-intent-baec1d2ef564>. [cited by applicant]
Google Search Central, “Search Engine Optimization (SEO) Starter Guide,” SEO Fundamentals, 3 pages, Accessed May 13, 2024, https://developers.google.com/search/docs/fundamentals/seo-starter-guide. [cited by applicant]
Google Search Central, “In-depth guide to how Google Search works,” SEO Fundamentals, 5 pages, Accessed May 13, 2024, https://developers.google.com/search/docs/fundamentals/how-search-works. [cited by applicant]
Google Search Central, “Do you need an SEO?” SEO Fundamentals, 6 pages, Accessed May 13, 2024, https://developers.google.com/search/docs/fundamentals/do-i-need-seo. [cited by applicant]
Google Search Central, “Google Search Essentials,” Documentation, 3 pages, Accessed May 13, 2024, <https://developers.google.com/search/docs/essentials>. [cited by applicant]
Open AI, “Introduction,” 3 pages, Accessed May 13, 2024, <https://platform.openai.com/docs/introduction>. [cited by applicant]
Open AI, “Text generation models,” 9 pages, Accessed May 13, 2024, <https://platform.openai.com/docs/guides/text-generation/chat-completions-api>. [cited by applicant]
Google Cloud, “Overview of the Gemini API in Vertex AI,” 7 pages, Accessed May 13, 2024, <https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/overview>. [cited by applicant]
SEMRush Team, “SEMRush Authority Score Explained and How It Works,” SEMRush Blog, 16 pages, Jan. 31, 2023, <https://www.semrush.com/blog/semrush-authority-score-explained>. [cited by applicant]
Handley, Rachel, “What Keywords Are & How to Use Them,” SEMRush Blog, 29 pages, Mar. 19, 2024, <https://www.semrush.com/blog/what-are-keywords/>. [cited by applicant]
Handley, Rachel, What Is Keyword Difficulty? (& How to Measure It), SEMRush Blog, 16 pages, Apr. 18, 2024, <https://www.semrush.com/blog/keyword-difficulty/>. [cited by applicant]
Byers, Kyle, “SERPs: Search Engine Results Pages Explained,” SEMRush Blog, 29 pages, Jan. 2, 2023, <https://www.semrush.com/blog/serp/>. [cited by applicant]
“Domain Authority,” Moz, 5 pages, Accessed May 13, 2024, <https://moz.com/learn/seo/domain-authority>. [cited by applicant]
“Welcome to Claude,” Anthropic, 4 pages, Accessed May 13, 2024, <https://docs.anthropic.com/en/docs/intro-to-claude>. [cited by applicant]
“ChatGPT,” Wikipedia, 19 pages, Accessed May 13, 2024, <https://en.wikipedia.org/wiki/ChatGPT>. [cited by applicant]
“Search engine optimization,” Wikipedia, 8 pages, Accessed May 13, 2024, <https://en.wikipedia.org/wiki/Search_engine_optimization>. [cited by applicant]
“Large Language Model,” Wikipedia, 13 pages, Accessed May 13, 2024, <https://en.wikipedia.org/wiki/Large_language_model>. [cited by applicant]
Cited By (1)
US 12,481,689