# US 2026/0099129 A1 · Connected home analytics system

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

- Number: US 2026/0099129 A1
- Document ID: US20260099129A1
- Status: Published application
- Kind: A1
- Application number: 18/962,903
- Filed: 2024-11-27
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Assignees: State Farm Mutual Automobile Insurance Company
- Applicants: State Farm Mutual Automobile Insurance Company
- Inventors: Ryan Michael Gross
- Web page: https://patentgrep.com/patent/US20260099129A1

## CPC

- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G05B 15/02: electric
- G05B 19/042: using digital processors (G05B19/05 takes precedence)
- G05B 2219/2642: Domotique, domestic, home control, automation, smart house
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

A connected home analytics system may (1) ingest first operational information from a first connected device of a domicile and second operational information from a second connected device of the domicile; (2) identify, using at least one machine learning model, one or more conditions of the domicile based upon a combination of the first operational information and the second operational information; and (3) initiate one or more actions responsive to identifying the one or more conditions of the domicile.

## Claims

### Claim 1

A connected home analytics system comprising:
one or more memory devices having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
ingesting first operational information from a first connected device of a domicile and second operational information from a second connected device of the domicile;
identifying, using at least one machine learning model, one or more conditions of the domicile based upon a combination of the first operational information and the second operational information; and
initiating one or more actions responsive to identifying the one or more conditions of the domicile.

### Claim 2 (depends on 1)

The connected home analytics system of claim 1, wherein the one or more actions comprise an automated response using one of the first connected device, the second connected device, or another connected device of the domicile.

### Claim 3 (depends on 1)

The connected home analytics system of claim 1, wherein the one or more actions comprise generating a notification regarding the one or more conditions of the domicile.

### Claim 4 (depends on 3)

The connected home analytics system of claim 3, wherein the notification includes a recommendation for responding to the one or more conditions of the domicile.

### Claim 5 (depends on 1)

The connected home analytics system of claim 1, wherein the at least one machine learning model comprises a large language model (LLM), and wherein identifying the one or more conditions of the domicile comprises:
determining, using the LLM, at least one first characteristic of the domicile based upon the first operational information and at least one second characteristic of the domicile based upon the second operational information;
identify, using the LLM, a correlation between the at least one first characteristic and the at least one second characteristic; and
identifying, using the LLM, the one or more conditions of the domicile based upon the correlation between the at least one first characteristic and the at least one second characteristic, wherein at least one of the correlation or the one or more conditions is inferred by the LLM and is not explicitly present in training data used to train the LLM.

### Claim 6 (depends on 1)

The connected home analytics system of claim 1, wherein at least one of the first connected device or the second connected device is enabled for wireless communication.

### Claim 7 (depends on 1)

The connected home analytics system of claim 1, wherein one of the first operational information or the second operational information includes an alert generated by the first connected device or the second connected device.

### Claim 8 (depends on 7)

The connected home analytics system of claim 7, wherein another of the first operational information or the second operational information includes one of a sensor reading or an operational state associated with the first connected device or the second connected device.

### Claim 9

A computer-implemented method for performing connected home analytics, the computer-implemented method comprising:
ingesting operational information from a first connected device of a domicile;
identifying, using at least one machine learning model, one or more conditions of the domicile based upon the first operational information;
identifying, using the at least one machine learning model, a second connected device of the domicile based upon the one or more conditions of the domicile and a functionality of the second connected device; and
initiating one or more actions for responding to the one or more conditions of the domicile using the second connected device responsive to identifying the one or more conditions of the domicile and to identifying the second connected device.

### Claim 10 (depends on 9)

The computer-implemented method of claim 9, wherein the at least one machine learning model comprises a large language model (LLM), and wherein identifying the second connected device comprises:
identify, using the LLM, a correlation between the one or more conditions and the functionality of the second connected device, wherein the correlation is inferred by the LLM and is not explicitly present in training data used to train the LLM.

### Claim 11 (depends on 9)

The computer-implemented method of claim 9, wherein at least one of the first connected device or the second connected device is enabled for wireless communication.

### Claim 12 (depends on 9)

The computer-implemented method of claim 9, wherein the operational information includes an alert generated by the first connected device.

### Claim 13 (depends on 9)

The computer-implemented method of claim 9, wherein the operational information includes one of a sensor reading or an operational state associated with the first connected device.

### Claim 14

A non-transitory computer-readable medium comprising instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
ingesting first operational information from a first connected device of a domicile and second operational information from a second connected device of the domicile;
determining, using at least one machine learning model, a first characteristic of the domicile based upon the first operational information and a second characteristic of the domicile based upon the second operational information;
identifying, using the at least one machine learning model, one or more conditions of the domicile based upon a correlation between the first characteristic and the second characteristic; and
initiating one or more actions responsive to identifying the one or more conditions of the domicile.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the one or more actions comprise an automated response using one of the first connected device, the second connected device, or another connected device of the domicile.

### Claim 16 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the one or more actions comprise generating a notification regarding the one or more conditions of the domicile.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the notification includes a recommendation for responding to the one or more conditions of the domicile.

### Claim 18 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the at least one machine learning model comprises a large language model (LMM), and wherein at least one of the correlation or the one or more conditions is inferred by the LLM and is not explicitly present in training data used to train the LLM.

### Claim 19 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein one of the first operational information or the second operational information includes an alert generated by the first connected device or the second connected device.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein another of the first operational information or the second operational information includes one of a sensor reading or an operational state associated with the first connected device or the second connected device.
