# US 2025/0165773 A1 · Ai based search and rescue technology platform

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

- Number: US 2025/0165773 A1
- Document ID: US20250165773A1
- Status: Published application
- Kind: A1
- Application number: 18/515,909
- Filed: 2023-11-21
- Published: 2025-05-22
- Earliest claimed: 2023-11-21
- Inventors: Martha Grabowski; Gwendolyn Morgan; Jean-Philippe Rancy; James McGarvey
- Web page: https://patentgrep.com/patent/US20250165773A1

## CPC

- G06N 3/08: Learning methods
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A search and rescue (SAR) application platform configured to provide SAR support services. A process includes: receiving, at a mission support system, mission data from structured and unstructured data feeds including data from an unmanned aerial system (UAS); outputting mission support information to a set of output nodes having disparate user interfaces (UIs), wherein at least one of the output nodes includes an augmented reality (AR) equipped device; and receiving, at a large language model (LLM), queries from the mission support system, and generating AI responses that augment the mission support information, wherein the LLM is trained with a model training system using structured and unstructured data sources involving SAR content.

## Claims

### Claim 1

A search and rescue (SAR) application platform, comprising:
a memory and a processor configured to provide SAR support services according to a process that includes:
receiving, at a mission support system, mission data from structured and unstructured data feeds including data from an unmanned aerial system (UAS);
outputting mission support information to a set of output nodes having disparate user interfaces (UIs), wherein at least one of the output nodes includes an augmented reality (AR) equipped device; and
receiving, at a large language model (LLM), queries from the mission support system, and generating AI responses that augment the mission support information, wherein the LLM is trained with a model training system using structured and unstructured data sources involving SAR content.

### Claim 2 (depends on 1)

The SAR application platform of claim 1, wherein the mission support information comprises UAS data and AI responses configured for display on the AR equipped device.

### Claim 3 (depends on 1)

The SAR application platform of claim 1, wherein the mission support information comprises communication, command and control (CCC) data and AI generated data.

### Claim 4 (depends on 1)

The SAR application platform of claim 1, wherein the mission support information comprises an initial SAR plan that includes AI generated data.

### Claim 5 (depends on 1)

The SAR application platform of claim 1, wherein the mission support system includes:
an input processor that stores mission data in a data cache; and
an LLM query processor that analyzes mission data in the data cache and generates queries for the LLM.

### Claim 6 (depends on 5)

The SAR application platform of claim 5, wherein the AI responses from the LLM are analyzed by an LLM response processor and formatted for the disparate UIs.

### Claim 7 (depends on 1)

The SAR application platform of claim 1, wherein the SAR content used to train the LLM comprises historical mission data.

### Claim 8 (depends on 1)

The SAR application platform of claim 1, wherein the structured SAR content used to train the LLM comprises environment data, communication data, inventory data and logistic data.

### Claim 9 (depends on 1)

The SAR application platform of claim 1, wherein the unstructured SAR content used to train the LLM comprises geological data, scientific data, sensor data, audio data, haptic data and social media data.

### Claim 10 (depends on 1)

The SAR application platform of claim 1, wherein the disparate UIs include a smartphone UI, a laptop UI, and an AR equipped device UI.

### Claim 11 (depends on 10)

The SAR application platform of claim 10, wherein the mission support information being output to the disparate UIs adheres to Universal Design (UD) principles.

### Claim 12 (depends on 1)

The SAR application platform of claim 1, wherein the mission support system is implemented using a uniform emergency and disaster response (EDR) application development infrastructure, wherein the EDR application development infrastructure comprises:
a set of middleware services, including application programming interfaces (APIs) and scripts; and
a set of data management services accessed via the middleware services that provide access to EDR data sources, and provide data integration among UAS devices, AR devices and LLM resources.

### Claim 13 (depends on 12)

The SAR application platform of claim 12, wherein the middleware services further include software modules and application templates.

### Claim 14 (depends on 12)

The SAR application platform of claim 12, wherein the data management services further comprise data security protocols.

### Claim 15

A method for providing search and rescue (SAR) support services, comprising:
receiving, at a mission support system, mission data from structured and unstructured data feeds including data from an unmanned aerial system (UAS);
outputting mission support information to a set of output nodes having disparate user interfaces (UIs), wherein at least one of the output nodes includes an augmented reality (AR) equipped device; and
receiving, at a generative artificial intelligence (AI) model, queries from the mission support system, and generating AI responses that augment the mission support information, wherein the generative AI model is trained using structured and unstructured data sources involving SAR content.

### Claim 16 (depends on 15)

The method of claim 15, wherein the mission support information comprises UAS data and AI responses configured for display on the AR equipped device.

### Claim 17 (depends on 15)

The method of claim 15, wherein the mission support information comprises an initial SAR plan that includes AI generated data.

### Claim 18 (depends on 15)

The method of claim 15, wherein the SAR content used to train the generative AI model comprises historical mission data, environment data, communication data, inventory data and logistic data.

### Claim 19

An emergency and disaster response (EDR) application platform, comprising:
a memory and a processor configured to provide EDR support services according to a process that includes:
receiving, at a mission support system, mission data from structured and unstructured data feeds including data from an unmanned aerial system (UAS);
outputting mission support information to a set of output nodes having disparate user interfaces (UIs), wherein at least one of the output nodes includes an augmented reality (AR) equipped device; and
receiving, at a large language model (LLM), queries from the mission support system, and generating AI responses that augment the mission support information, wherein the LLM is trained with a model training system using structured and unstructured data sources involving EDR content.

### Claim 20

The EDR application platform is selected from a group consisting of: structural integrity assessment, search and rescue, emergency supply delivery, mapping and surveillance, and post disaster relief.
