IP Library › Granted Patent US 12,631,514
Granted Patent B2
US 12,631,514 · App. 18/095,675 · Granted May 19, 2026

Systems and methods for detecting and preventing damage to pipes

Inventors: Brian N. Harvey (Bloomington, IL); Vicki King (Bloomington, IL)
Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE
G01M3/243G01M3/007
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,631,514
App. No.
18/095,675
Granted
May 19, 2026
Kind
B2
Abstract

Systems and methods are described for detecting a leak based upon home telematics data. The method may include: (1) receiving home telematics data from one or more sensors associated with one or more pipes (or piping systems) in a structure, wherein the home telematics data is indicative of the frequency with which the one or more pipes are being used; (2) determining, using a trained machine learning algorithm, pipe activity associated with the one or more pipes is occurring at an irregular frequency; (3) determining, based upon at least the determination that the pipe activity associated with the one or more pipes is occurring at the irregular frequency, that the one or more pipes are leaking; and (4) transmitting an indication to a user associated with the home that the one or more pipes are leaking.

Claims (57)

1 . A computer-implemented method for detecting a leak based upon home telematics data, the computer-implemented method comprising:

receiving, by one or more processors, home telematics data from one or more sensors associated with one or more pipes in a structure and occupancy data associated with at least part of the structure, wherein the home telematics data is indicative of a frequency with which the one or more pipes are being used;

determining, by the one or more processors and using a trained machine learning algorithm, pipe activity associated with the one or more pipes is occurring at an irregular frequency based upon at least the frequency and the occupancy data;

determining, by the one or more processors and based upon at least the determination that the pipe activity associated with the one or more pipes is occurring at the irregular frequency, that the one or more pipes are leaking; and

performing, by the one or more processors and based upon the occupancy data, at least one of:

initiating, by the one or more processors, one or more preventative actions when the occupancy data indicates a user associated with the structure is not present at the structure, or

transmitting, by the one or more processors, an indication to the user associated with the structure that the one or more pipes are leaking when the occupancy data indicates the user is present at the structure.

2 . The computer-implemented method of claim 1 , further comprising:

generating, during an initial calibration phase, a model for regular pipe activity associated with the one or more pipes;

wherein the determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency is based at least upon the model.

3 . The computer-implemented method of claim 1 , wherein the one or more sensors include at least one of: (i) vibration sensors; (ii) audio sensors, (iii) visual sensors, (iv) humidity sensors, or (v) conductivity sensors.

4 . The computer-implemented method of claim 3 , wherein the one or more sensors include at least the visual sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more visual indicators, wherein the one or more visual indicators are indicative of dripping water.

5 . The computer-implemented method of claim 3 , wherein the one or more sensors include at least the audio sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more audio indicators, wherein the one or more audio indicators are indicative of dripping water.

6 . The computer-implemented method of claim 1 , wherein the indication to the user includes at least one of: (i) an alert through a mobile application; (ii) a text message; or (iii) an audio alert through a user device.

7 . The computer-implemented method of claim 1 , further comprising:

generating one or more recommendations for a response;

wherein the indication to the user includes the one or more recommendations for the response.

8 . A computing device for detecting a leak based upon home telematics data, the computing device comprising:

one or more processors;

a communication unit; and

a non-transitory computer-readable medium coupled to the one or more processors and the communication unit and storing instructions thereon that, when executed by the one or more processors, cause the computing device to:

receive home telematics data from one or more sensors associated with one or more pipes in a structure and occupancy data associated with at least part of the structure, wherein the home telematics data is indicative of a frequency with which the one or more pipes are being used;

determine, using a trained machine learning algorithm, pipe activity associated with the one or more pipes is occurring at an irregular frequency based upon at least the frequency and the occupancy data;

determine, based upon at least the determination that the pipe activity associated with the one or more pipes is occurring at the irregular frequency, that the one or more pipes are leaking; and

perform, based upon the occupancy data, at least one of:

initiating one or more preventative actions when the occupancy data indicates a user associated with the structure is not present at the structure, or

transmitting an indication to the user associated with the structure that the one or more pipes are leaking when the occupancy data indicates the user is present at the structure.

9 . The computing device of claim 8 , wherein the non-transitory computer-readable medium further include instructions that, when executed by the one or more processors, cause the computing device to:

generate, during an initial calibration phase, a model for regular pipe activity associated with the one or more pipes;

wherein determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency is based at least upon the model.

10 . The computing device of claim 8 , wherein the one or more sensors include at least one of: (i) vibration sensors; (ii) audio sensors, (iii) visual sensors, (iv) humidity sensors, or (v) conductivity sensors.

11 . The computing device of claim 10 , wherein the one or more sensors include at least the visual sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more visual indicators, wherein the one or more visual indicators are indicative of dripping water.

12 . The computing device of claim 10 , wherein the one or more sensors include at least the audio sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more audio indicators, wherein the one or more audio indicators are indicative of dripping water.

13 . The computing device of claim 8 , wherein the indication to the user includes at least one of: (i) an alert through a mobile application; (ii) a text message; or (iii) an audio alert through a user device.

14 . The computing device of claim 8 , wherein the non-transitory computer-readable medium further include instructions that, when executed by the one or more processors, cause the computing device to:

generate one or more recommendations for a response;

wherein the indication to the user includes the one or more recommendations for the response.

15 . A tangible, non-transitory computer-readable medium storing instructions for detecting a leak based upon home telematics data that, when executed by one or more processors of a computing device, cause the computing device to:

receive home telematics data from one or more sensors associated with one or more pipes in a structure and occupancy data associated with at least part of the structure, wherein the home telematics data is indicative of a frequency with which the one or more pipes are being used;

determine, using a trained machine learning algorithm, pipe activity associated with the one or more pipes is occurring at an irregular frequency based upon at least the frequency and the occupancy data;

determine, based upon at least the determination that the pipe activity associated with the one or more pipes is occurring at the irregular frequency, that the one or more pipes are leaking; and

perform, based upon the occupancy data, at least one of:

initiating one or more preventative actions when the occupancy data indicates a user associated with the structure is not present at the structure, or

transmitting an indication to the user associated with the structure that the one or more pipes are leaking when the occupancy data indicates the user is present at the structure.

16 . The tangible, non-transitory computer-readable medium of claim 15 , wherein the tangible, non-transitory computer-readable medium further includes instructions that, when executed by the one or more processors, cause the computing device to:

generate, during an initial calibration phase, a model for regular pipe activity associated with the one or more pipes;

wherein determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency is based at least upon the model.

17 . The tangible, non-transitory computer-readable medium of claim 15 , wherein the one or more sensors include at least one of: (i) vibration sensors; (ii) audio sensors, (iii) visual sensors, (iv) humidity sensors, or (v) conductivity sensors.

18 . The tangible, non-transitory computer-readable medium of claim 17 , wherein the one or more sensors include at least the visual sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more visual indicators, wherein the one or more visual indicators are indicative of dripping water.

19 . The tangible, non-transitory computer-readable medium of claim 18 , wherein the one or more sensors include at least the audio sensors, and determining that the pipe activity associated with the one or more pipes is occurring at the irregular frequency includes:

detecting a presence of one or more audio indicators, wherein the one or more audio indicators are indicative of dripping water.

20 . The tangible, non-transitory computer-readable medium of claim 18 , wherein the indication to the user includes at least one of: (i) an alert through a mobile application; (ii) a text message; or (iii) an audio alert through a user device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 1, 2023
From: HARVEY, BRIAN N.; KING, VICKI
To: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Reel/Frame 062565/0092 →
Continuity (5)
Provisional Application 63437257 · Jan 5, 2023
Provisional Application 63426890 · Nov 21, 2022
Provisional Application 63425541 · Nov 15, 2022
Provisional Application 63421445 · Nov 1, 2022
Related Publication 20240142330A1 · May 2, 2024
References Cited (25)
US 5139044A · Otten et al. · 1992 [cited by applicant]
US 6105607A · Caise et al. · 2000 [cited by applicant]
US 6439260B1 · Shuff · 2002 [cited by applicant]
US 6696961B2 · Uhler · 2004 [cited by applicant]
US 7299814B2 · Fenton · 2007 [cited by applicant]
US 10546469B2 · Peterson et al. · 2020 [cited by applicant]
US 10579075B2 · Tahan et al. · 2020 [cited by applicant]
US 10685402B1 · Bryant et al. · 2020 [cited by applicant]
US 11047761B1 · Frackelton · 2021 [cited by examiner]
US 11354748B1 · Bryant · 2022 [cited by examiner]
US 20060191323A1 · Garabedian et al. · 2006 [cited by applicant]
US 20130049950A1 · Wohlert · 2013 [cited by applicant]
US 20140238511A1 · Klicpera · 2014 [cited by applicant]
US 20140244997A1 · Goel et al. · 2014 [cited by applicant]
US 20140358592A1 · Wedig et al. · 2014 [cited by applicant]
US 20160078744A1 · Gieck · 2016 [cited by applicant]
US 20160161940A1 · Max · 2016 [cited by examiner]
US 20170009432A1 · Lapointe et al. · 2017 [cited by applicant]
US 20170292893A1 · Bunker · 2017 [cited by examiner]
US 20190368964A1 · Inoue · 2019 [cited by examiner]
US 20220205956A1 · Stephens · 2022 [cited by examiner]
US 20220261921A1 · Bryant · 2022 [cited by examiner]
US 20220412835A1 · Sewell · 2022 [cited by examiner]
US 20230334646A1 · Ziola · 2023 [cited by examiner]
U.S. Appl. No. 18/095,678, filed Jan. 11, 2023. [cited by applicant]