# US 2025/0378518 A1 · Systems and methods for generating adaptive artificial intelligence-based course templates using real-time feedback

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

- Number: US 2025/0378518 A1
- Document ID: US20250378518A1
- Status: Published application
- Kind: A1
- Application number: 18/734,860
- Filed: 2024-06-05
- Published: 2025-12-11
- Earliest claimed: 2024-06-05
- Assignees: Pearson Education, Inc.
- Applicants: Pearson Education, Inc.
- Inventors: Thomas K. NOVATIN; Chie Voy LOURNG; Sudhakara Rao MADDINENI; Peerajirao Dongarekar PRITHVIRAJ; Shripati Shridhar NAVANAGERI
- Web page: https://patentgrep.com/patent/US20250378518A1

## CPC

- G06Q 50/205: {Education administration or guidance}
- G06Q 50/20: Education
- H04L 67/306: User profiles
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods for adaptive artificial intelligence-based course template generation. One system may include a processing system configured to: receive a request to generate a first course template for a course; identify, with an artificial intelligence (AI) engine, user data that is contextually relevant to the request; synthesize, with the AI engine, the user data to determine a set of patterns for the user data; generate, with the AI engine, a set of recommendations based on the set of patterns; generate, based on the set of recommendations, a first course template for the course; generate a first set of learning course content that adheres to the first course template for the course; and transmit the first set of learning course content to a client device for display as a learning course content rendering via a graphical user interface.

## Claims

### Claim 1

A system for implementing adaptive artificial intelligence-based course template generation, the system comprising:
a processing system including one or more electronic processors, the processing system configured to:
receive a request to generate a first course template for a course;
identify, with an artificial intelligence (AI) engine, user data that is contextually relevant to the request;
synthesize, with the AI engine, the user data to determine a set of patterns for the user data;
generate, with the AI engine, a set of recommendations based on the set of patterns;
generate, based on the set of recommendations, a first course template for the course;
generate a first set of learning course content that adheres to the first course template for the course; and
transmit, via a communication network, the first set of learning course content to a client device for display as a learning course content rendering via a graphical user interface.

### Claim 2 (depends on 1)

The system of claim 1, wherein the AI engine includes:
a retriever-augmented generation (RAG) model configured to identify the user data that is contextually relevant to the request and synthesize the user data to determine the set of patterns for the user data; and
a recommendation model configured to generate the set of recommendations based on the set of patterns.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processing system is configured to:
receive feedback data associated with the first set of learning course content;
generate, with the AI engine, a second course template for the course based on the feedback data;
generate a second set of learning course content that adheres to the second course template for the course; and
transmit the second set of learning course content for display.

### Claim 4 (depends on 3)

The system of claim 3, wherein the second course template is different from the first course template, and the first course template and the second course template comply with the same learning objective of the course.

### Claim 5 (depends on 3)

The system of claim 3, wherein the feedback data includes learner user data for a learner user of the course, the learner user data including at least one of data describing an interaction of the learner user with the first set of learning course content, a performance metric of the learner user, or qualitative feedback provided by the learner user.

### Claim 6 (depends on 3)

The system of claim 3, wherein the feedback data includes instructor user data for an instructor user of the course, the instructor user data including a preference of the instructor user.

### Claim 7 (depends on 3)

The system of claim 3, wherein the second course template includes additional course content not included in the first course template.

### Claim 8 (depends on 3)

The system of claim 3, wherein the processing system is configured to transmit the first set of learning course content to a first client device of a first learner user and a second client device of a second learner user, and, when the feedback data indicates that the second learner user achieved a performance metric below a performance threshold, transmit the second set of learning course content to the second client device of the second learner user, wherein the second set of learning course content includes supplemental course content.

### Claim 9 (depends on 1)

The system of claim 1, wherein the processing system is configured to:
develop and maintain a plurality of learner user profiles, each learner user profile of the plurality of learner user profiles being specific to a specific learner user and including at least one of learner user interaction data, performance metric data, or qualitative feedback data.

### Claim 10 (depends on 1)

The system of claim 1, wherein the user data includes a course criterion established by an instructor user of the course, and wherein the processing system is configured to determine an impact of the course criterion on one or more learner users of the course.

### Claim 11 (depends on 1)

The system of claim 1, wherein the user data includes a recording of an instructor user of the course, and wherein the processing system is configured to generate the course template based on the recording and generate, on a personalized basis for a learner user, the first set of learning course content based on the recording to emulate a teaching style of the instructor user.

### Claim 12 (depends on 1)

The system of claim 1, wherein, when the request identifies a first learner user, the user data includes user data included in a learner profile of the first learner user and the first course template is generated for a first learner user such that the first course template is personalized for the first learner user.

### Claim 13 (depends on 1)

The system of claim 1, wherein, when the request identifies a group of learner users, the user data includes user data included in a plurality of learner profiles for the group of learner users and the first course template is generated for the group of learner users such that the first course template is personalized for the group of learner users.

### Claim 14

A method of implementing adaptive artificial intelligence-based course template generation, the method comprising:
receiving, with a processing system including one or more electronic processors, while a course is in progress, data associated with a first set of learning course content for the course, the first set of learning course content adhering to a first course template for the course, the first course template generated using an artificial intelligence (“AI”) engine;
providing, with the processing system, the data to the AI engine in order to determine a recommended course template modification;
generating, with the processing system, using the AI engine, a second course template for the course based on the recommended course template modification;
generating, with the processing system, a second set of learning course content that adheres to the second course template for the course; and
transmitting, with the processing system via a communication network, the second set of learning course content to a client device for display as a learning course content rendering via a graphical user interface.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
identifying, with a retriever-augmented generation (RAG) model of the AI engine, user data that is contextually relevant;
synthesizing, with the RAG model of the AI engine, the user data;
determining, with the RAG model of the AI engine, a set of patterns for the user data; and
generating, with a recommendation model, a set of recommendations based on the set of patterns, the set of recommendations including the recommended course template modification.

### Claim 16 (depends on 14)

The method of claim 14, wherein generating the second course template includes generating a second course template that is different from the first course template, wherein the first course template and the second course template comply with a course criterion established by an instructor user of the course.

### Claim 17

A non-transitory, computer-readable medium storing instructions that, when executed by a processing system including one or more electronic processors, perform a set of functions, the set of functions comprising:
receiving a request to generate a first course template for a course;
generating, using an artificial intelligence (AI) engine, a first course template for the course, the first course template identifying a first set of learning course content that adheres to the first course template for the course;
transmitting the first set of learning course content for display as a learning course content rendering via a graphical user interface;
receiving feedback data associated with the first set of learning course content;
generating, with the AI engine, a second course template for the course based on the feedback data, the second course template identifying a second set of learning course content that adheres to the second course template for the course; and
transmitting the second set of learning course content for display.

### Claim 18 (depends on 17)

The computer-readable medium of claim 17, wherein generating the first course template for the course by:
identifying, with a retriever-augmented generation (RAG) model of the AI engine, user data that is contextually relevant to the request;
synthesizing, with the RAG model, the user data to determine a set of patterns for the user data; and
generating, with a recommendation model of the AI engine, a set of recommendations based on the set of patterns.

### Claim 19 (depends on 17)

The computer-readable medium of claim 17,
wherein transmitting the first set of learning course content includes transmitting the first set of learning course content to a first client device of a first learner user of the course and a second client device of a second learner user of the course, and
wherein transmitting the second set of learning course content includes, when the feedback data indicates that the second learner user achieved a performance metric below a performance threshold, transmitting the second set of learning course content to the second client device of the second learner user, wherein the second set of learning course content includes supplemental course content.

### Claim 20 (depends on 17)

The computer-readable medium of claim 17, wherein generating the second course template includes generating a second course template that is different from the first course template, wherein the first course template and the second course template comply with a course criterion established by an instructor user of the course.
