# US 2025/0166484 A1 · Computer-implemented method of alerting a property manager of a roof pooling issue

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

- Number: US 2025/0166484 A1
- Document ID: US20250166484A1
- Status: Published application
- Kind: A1
- Application number: 18/951,774
- Filed: 2024-11-19
- Published: 2025-05-22
- Earliest claimed: 2023-11-20
- Assignees: Technologies Domely
- Applicants: Technologies Domely
- Inventors: Abdelrahmane FERCHICHI; Ahmed ATOUBI; Charlphillip BOUTET; Jonathan BOUCHER
- Web page: https://patentgrep.com/patent/US20250166484A1

## CPC

- G08B 21/20: responsive to moisture
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/176: {Urban or other man-made structures}
- G06V 2201/10: Recognition assisted with metadata
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The computer-implemented method of alerting a property manager of a pooling issue pertaining to a roof of a building can include: providing image data including an image of the roof of the building; determining that water pooling is present in the image the roof of the building, including processing the image of the roof of the building using a trained convolutional neural network; providing contextual data pertaining to at least one of weather, history, and drain obstruction associated to the determined water pooling; determining that the determined water pooling is indicative of the pooling issue, including validating a contextual criteria against the contextual data; and transmitting an alert to the property manager contingent upon said determining that the determined water pooling is indicative of the pooling issue.

## Claims

### Claim 1

A computer-implemented method of alerting a property manager of a pooling issue pertaining to a roof of a building, the method comprising:
providing image data including an image of the roof of the building;
determining that water pooling is present in the image the roof of the building, including processing the image of the roof of the building using a trained convolutional neural network;
providing contextual data pertaining to at least one of weather, history, and drain obstruction associated to the determined water pooling;
determining that the determined water pooling is indicative of the pooling issue, including validating a contextual criteria against the contextual data; and
transmitting an alert to the property manager contingent upon said determining that the determined water pooling is indicative of the pooling issue.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1 wherein said providing image data includes, using a camera, taking the image of the roof of the building, transmitting the image of the roof of the building over a telecommunications network, and storing the image of the roof of the building in a non-transitory computer-readable memory.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1 wherein said image data includes metadata associated to the image of the roof of the building, the metadata including a timestamp of a moment in time at which the image of the roof of the building was taken, wherein said validating the contextual criteria against the contextual data factors in the moment in time at which the image of the roof of the building was taken via the timestamp.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3 wherein the contextual criteria pertains contextual data dating from less than 4 days before the moment in time at which the image of the roof of the building was taken.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3 wherein the contextual data includes a weather history pertaining to a location at which the image of the roof of the building was taken, said validating the contextual criteria against the contextual data includes determining, from the weather history, an absence of rain at one or more moments in time preceding the moment in time at which the image of the roof of the building was taken.

### Claim 6 (depends on 3)

The computer-implemented method of claim 3 wherein the image of the roof of the building is a first image of the roof of the building, the image data includes a plurality of additional images of the roof of the building taken at different moments in time associated to respective timestamps, the contextual data includes a history of previous determinations of whether or not water pooling was present in respective ones of the additional images of the roof, said validating the contextual criteria against the contextual data includes determining, from the history of previous determinations, an absence of rain at one or more of said different moments in time.

### Claim 7 (depends on 5)

The computer-implemented method of claim 5 wherein the contextual data includes a weather history pertaining to a location at which the image of the roof of the building was taken, said validating the contextual criteria against the contextual data further includes determining, from the weather history, an absence of rain at one or more moments in time preceding the moment in time at which the image of the roof of the building was taken, said transmitting the alert to the property manager being contingent upon both said determining, from the history of previous determinations, the absence of rain at one or more of said different moments in time and determining, from the weather history, an absence of rain at one or more moments in time preceding the moment in time at which the image of the roof of the building was taken.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1 wherein the contextual data includes weather data pertaining to a location of the roof of the building, and said determining that the determined water pooling is indicative of the pooling issue includes validating an absence of rain in the weather data.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1 wherein the image of the roof of the building is a first image of the roof of the building, the image data includes a plurality of additional images of the roof of the building taken at different moments in time associated to respective timestamps, further comprising determining that a drain is present in at least one of the additional images of the roof using the trained convolutional neural network, wherein said determining that the determined water pooling is indicative of the pooling issue including validating that the drain was determined as present in at least one of the additional images of the roof.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1 wherein the image of the roof of the building is a first image of the roof of the building, the image data includes a plurality of additional images of the roof of the building taken at different moments in time associated to respective timestamps, further comprising determining that debris is present in at least one of the additional images of the roof using the trained convolutional neural network, storing said determination that debris is present in association with the respective at least one of the additional images of the roof, wherein said determining that the determined water pooling is indicative of the pooling issue includes validating that the debris was determined as present in said at least one of the additional images of the roof.

### Claim 11 (depends on 9)

The computer-implemented method of claim 9 further comprising determining that a drain is present in at least one of the additional images of the roof using the trained convolutional neural network, wherein said determining that the determined water pooling is indicative of the pooling issue further includes validating that the drain was determined as present in at least one of the additional images of the roof.
