# US 2026/0017537 A1 · Edge deployed digital training platform

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

- Number: US 2026/0017537 A1
- Document ID: US20260017537A1
- Status: Published application
- Kind: A1
- Application number: 19/266,782
- Filed: 2025-07-11
- Published: 2026-01-15
- Earliest claimed: 2024-07-11
- Assignees: Obrizum Group Ltd.
- Applicants: Obrizum Group Ltd.
- Inventors: Chibeza Chintu AGLEY; Olivier Rene M. VAN ACKER
- Web page: https://patentgrep.com/patent/US20260017537A1

## CPC

- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G09B 5/02: with visual presentation of the material to be studied, e.g. using film strip
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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)

## Abstract

The present disclosure includes a training system to present training experiences to users in low-bandwidth, intermittent, or no network connectivity. In some embodiments, such as during periods of low-bandwidth wide area network connectivity or no connectivity for specific parts of the system because of security restrictions, the training system may store media assets and user profile information in local storage and communicate with a remote artificial intelligence model across a wide area network to generate a training experience. In other embodiments, such as during intermittent wide area network connectivity, the training system may retrieve and store media assets, user profile information, and a local artificial intelligence model in local storage during periods when wide area network connection is available. The training system may then generate a training experience from the media assets and the local artificial intelligence model.

## Claims

### Claim 1

A computer-implemented method for presenting a training experience, comprising:
identifying, via a processor, training content relevant to the training experience based on a knowledge base;
storing, via the processor, the training content and a local artificial intelligence model into a local storage on a computer device in a deployment environment;
transmitting, via the processor, the training content to a user device for display via a user interface;
receiving, via the processor, user inputs based on the training content;
re-simulating, via the processor, a remote computing system using the user inputs during a first connectivity state, wherein re-simulating the remote computing system comprises re-simulating the training experience based on the user inputs to update the knowledge base representing an expected training experience; and
updating, via the processor, the local storage with updated training content during a second connectivity state, the updated training content produced by the remote computing system during the re-simulation.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the first connectivity state is a first period of wide area network connectivity; and
the second connectivity state a distinct second period of wide area network connectivity.

### Claim 3 (depends on 1)

The method of claim 1, wherein transmitting the training content comprises:
generating, via the processor, the training experience based on the training content and the local artificial intelligence model; and
transmitting, via the processor, the training experience to the user device.

### Claim 4 (depends on 1)

The method of claim 1, wherein the local storage comprises:
a low security local storage accessible via a local area network and a global wide area network; and
a high security local storage only accessible via a local area network.

### Claim 5 (depends on 4)

The method of claim 4, wherein storing training content and a local artificial intelligence model into a local storage comprises:
categorizing, via the processor, the training content into high security training content and low security training content;
storing, via the processor, the high security training content in the high security local storage; and
storing, via the processor, the low security training content in the low security local storage.

### Claim 6 (depends on 1)

The method of claim 1, wherein transmitting the training content and receiving user inputs comprises communicating with the user device via a local area network.

### Claim 7 (depends on 1)

The method of claim 1, wherein identifying the training content comprises identifying, via the processor, a plurality of nodes of the knowledge space representing a plurality of training content related to a mixture of training concepts that make up a training subject.

### Claim 8 (depends on 1)

The method of claim 1, wherein the remote computing system comprises a remote artificial intelligence model, and wherein updating the local storage further comprises updating, via the processor, the local artificial intelligence model based on the remote artificial intelligence model of the remote computing system.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
receiving, via the processor, aggregate data of multiple users representing interactions of the multiple users with the training content; and
updating, via the processor, a knowledge base representation of the training content based on the aggregate data.

### Claim 10

A computer-implemented method for deploying a training platform comprising:
receiving, via a processor of a computing device, a request to engage with the training platform;
identifying, via the processor, training platform data relevant to a training experience based on a knowledge base;
retrieving, via the processor, the training platform data and a local artificial intelligence model of the training platform from a local storage in communication with the computing device;
outputting, via the processor, a user interface configured to display the training experience based on the training platform data and local artificial intelligence model;
receiving, via the processor, user engagement data based on user interaction with the training experience, the user engagement data including a training journey and user inputs;
storing, via the processor, the user engagement data in the local storage; and
transmitting, via the processor, the user engagement data to a remote computing system to enable the remote computing system to re-simulate the user interaction and to generate updated user profile data for the training platform.

### Claim 11 (depends on 10)

The method of claim 10, wherein the training platform data comprises training content files and user profile information.

### Claim 12 (depends on 10)

The method of claim 10, wherein the user request is received through communication with a user device across a local area network.

### Claim 13 (depends on 10)

The method of claim 10, wherein outputting the user interface comprises:
generating, via the processor, the training experience based on the training platform data and the local artificial intelligence model;
generating, via the processor, the user interface configured to display the training experience; and
causing display, via the processor, the user interface at the user device.

### Claim 14 (depends on 13)

The method of claim 13, wherein transmitting the training experience and receiving the user inputs comprises communicating with a user device across a local area network.

### Claim 15 (depends on 10)

The method of claim 10, wherein the updated user profile data comprises the user training journey and an evaluation of the user engagement generated by the remote computing system.

### Claim 16

A computer-implemented method for presenting training content, comprising:
identifying, via a processor, training platform data relevant to a training experience based on a knowledge base;
storing, via the processor, the training platform data into local storage on a computer device;
transmitting, via the processor, training content to a user device for display via a user interface;
receiving, via the processor, user inputs in response to the training content;
communicating, via the processor, the user inputs to a remote artificial intelligence model via a wide area network connection; and
receiving, via the processor, content selections from the remote artificial intelligence model.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
retrieving, via the processor, training content items from the training platform data in the local storage based on the content selections; and
transmitting, via the processor, the training content items to the user device.

### Claim 18 (depends on 16)

The method of claim 16, wherein the training platform data comprises training content files and user profile information.

### Claim 19 (depends on 16)

The method of claim 16, wherein transmitting training content comprises:
generating, via the processor, the training experience from the training platform data and through communication with the remote artificial intelligence model via the wide area network connection; and
transmitting, via the processor, the training experience to the user device.

### Claim 20 (depends on 16)

The method of claim 16, wherein transmitting the training content and receiving the user inputs comprises communicating with a user device across a local area network.
