# US 2026/0073805 A1 · Fill-in-the-blank question generation system aligned with educational curriculum for a user using integrated programmatic control and specialized guided and constrained artificial intelligence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073805 A1
- Document ID: US20260073805A1
- Status: Published application
- Kind: A1
- Application number: 19/273,077
- Filed: 2025-07-17
- Published: 2026-03-12
- Earliest claimed: 2024-07-17
- Assignees: 2hr Learning, Inc.
- Applicants: 2hr Learning, Inc.
- Inventors: Niraj Patel; Janet Demir; Sean Carlson; Nima Shirazian
- Web page: https://patentgrep.com/patent/US20260073805A1

## CPC

- G09B 7/02: of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
- G06Q 50/205: {Education administration or guidance}
- G09B 7/04: characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question or supplying a further explanation
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A fill-in-the-blank generation system and method integrates programmatic control and a guided and constrained AI engine to generate a fill-in-the-blank (FITB) question aligned with the educational curriculum of the user. The study mode delivery system accesses the data from the educational standards database and historical database. The study mode delivery system receives a standard description and set of key terms from the data accessed from the databases. The analyzer integrated within the study mode delivery system analyzes the course, standard description, and key terms relevant to the educational curriculum and standards.

## Claims

### Claim 1

A method that integrates programmatic control and a guided and constrained Artificial Intelligence (AI) engine to generate fill-in-the-blank (FITB) questions aligned with the educational curriculum for a user comprising:
executing code using one or more processors of a computer system to cause the computer system to perform operations comprising:
accessing an educational standards database and historical database by a study mode delivery system to retrieve relevant educational content;
receiving a standard description and a set of key terms from the relevant educational content from a user profile, educational standards, and historical database accessed by the study mode delivery system;
utilizing a natural language processing (NLP) model by an analyzer to analyze the received educational content;
generating a prompt by a prompt generator to guide the AI engine to generate an initial FITB question, including a corresponding answer and learning content based on the standard description and the set of key terms;
transferring the prompt to the AI engine to generate the FITB question, along with the corresponding answer and learning content; and
guiding and constraining the AI engine using an engineered prompt to refine the initially generated FITB question to generate the final FITB question, along with the corresponding answer and learning content by aligning with the educational standard and learning content.

### Claim 2 (depends on 1)

The method of claim 1 further comprising:
generating a grader assistant prompt for identifying the correctness of the user response on the refined generated FITB question; and
transferring the grader assistant prompt to the AI engine to check the correctness of the user response on the online learning platform.

### Claim 3 (depends on 1)

The method of claim 1 wherein the generated FITB question embeds unique contextual clues, ensuring that the answer provided by the user is uniquely identifiable and correct based on the detailed context given in the FITB question.

### Claim 4 (depends on 1)

The method of claim 1 further comprising:
developing learning content designed to align with the FITB question, wherein the learning content is structured to provide comprehensive knowledge necessary to answer the FITB question without directly hinting at the answer.

### Claim 5 (depends on 1)

The method of claim 1 further comprising:
identifying if quality criteria of the generated initial FITB question is not met, then the AI engine is configured to regenerate the fill-in-the-blank question and learning content using the AI ENGINE.

### Claim 6 (depends on 1)

The method of claim 1 wherein the quality criteria includes automated validation against a set of predefined checks such as relevance, clarity, difficulty level, and grammatical correctness.

### Claim 7 (depends on 1)

The method of claim 1 wherein the AI ENGINE is trained using a dataset specifically curated for educational content to enhance the relevance and accuracy of the generated fill in the blank questions.

### Claim 8 (depends on 1)

The method of claim 1 wherein the educational standards include Common Core State Standards (CCSS), Next Generation Science Standards (NGSS), and Advanced Placement (AP).

### Claim 9 (depends on 1)

The method of claim 1 wherein storing the generated FITB questions and learning content in a data repository.

### Claim 10

A system that integrates programmatic control and a guided and constrained Artificial Intelligence (AI) engine to generate fill-in-the-blank (FITB) questions aligned with the educational curriculum for a user comprising:
one or more processors of a computer system; and
a memory, coupled to the one or more processors, storing code that when executed causes the computer system to perform operations comprising:
accessing an educational standards database and historical database by a study mode delivery system to retrieve relevant educational content;
receiving a standard description and a set of key terms from the relevant educational content from a user profile accessed by the study mode delivery system;
utilizing a natural language processing (NLP) model by an analyzer to analyze the received educational content;
generating a prompt by a prompt generator to guide the AI engine to generate an initial FITB question, including a corresponding answer and learning content based on the standard description and the set of key terms;
transferring the prompt to the AI engine to generate the FITB question, along with the corresponding answer and learning content; and
guiding and constraining an AI engine using an engineered prompt to refine the initially generated FITB question to generate the final FITB question, along with the corresponding answer and learning content by aligning with the educational standard and learning content.

### Claim 11 (depends on 9)

The system of claim 9 wherein the generated FITB question embeds unique contextual clues, ensuring that the answer provided by the user is uniquely identifiable and correct based on the detailed context given in the FITB question.

### Claim 12 (depends on 9)

The system of claim 9 wherein the memory stores code that when executed causes the computer system to further perform operations comprising:
developing learning content designed to align with the FITB question, wherein the learning content is structured to provide comprehensive knowledge necessary to answer the FITB question without directly hinting at the answer.

### Claim 13 (depends on 9)

The system of claim 9 wherein the memory stores code that when executed causes the computer system to further perform operations comprising:
identifying if the quality criteria of the generated initial FITB question is not met, then the AI engine is configured to regenerate the fill-in-the-blank question and learning content using the AI ENGINE.

### Claim 14 (depends on 9)

The system of claim 9 wherein the quality criteria includes automated validation against a set of predefined checks such as relevance, clarity, difficulty level, and grammatical correctness.

### Claim 15 (depends on 9)

The system of claim 9 wherein the AI ENGINE is trained using a dataset specifically curated for educational content to enhance the relevance and accuracy of the generated FITB questions.

### Claim 16 (depends on 9)

The system of claim 9 wherein the educational standards include Common Core State Standards (CCSS), Next Generation Science Standards (NGSS), and Advanced Placement (AP).

### Claim 17 (depends on 9)

The system of claim 9 wherein storing the generated FITB questions and learning content in a data repository.
