Determining optimal water sensor placement using machine learning
View Patent ↗Systems and methods disclosed herein relate to determining optimal placement location of one or more water sensors proximate a structure using machine learning. The machine learning model may be provided structure information for a structure at which the water sensors are to be placed, and generate an indication of the optimal placement location of the one or more water sensors proximate the structure. The optimal placement location of the water sensors may correspond to potential sources of water damage. A user device may receive the indication of the optimal placement location of the one or more water sensors proximate the structure to a user device.
1 . A computer-implemented method for determining an optimal placement location of one or more water sensors proximate a structure using machine learning, the method comprising:
obtaining, by one or more processors, structure information for a structure at which the one or more water sensors are to be placed;
providing, by the one or more processors, the structure information to a trained machine learning model to generate an indication of the optimal placement location of the one or more water sensors proximate the structure, wherein:
the trained machine learning model is trained using historical water damage claims data,
the historical water damage claims data includes a geographic location of a structure associated with the corresponding historical water damage claims data,
the trained machine learning model is configured to learn a relationship between building code requirements for the geographic locations and potential sources of water damage, and
the optimal placement location of the one or more water sensors corresponds to the potential sources of water damage; and
providing, by the one or more processors, the indication of the optimal placement location of the one or more water sensors proximate the structure to a user device.
2 . The computer-implemented method of claim 1 , wherein the structure information includes data associated with one or more of a floorplan of the structure, structural components of the structure, a property the structure is located upon, plumbing at the structure, and/or appliances at the structure.
3 . The computer-implemented method of claim 1 , wherein the structure information includes a geographic location of the structure.
4 . The computer-implemented method of claim 1 , wherein the machine learning model is further configured to weight one or more attributes of the structure information.
5 . The computer-implemented method of claim 1 , wherein the machine learning model is further configured to:
determine a score associated with the potential sources of water damage; and
rank the potential sources of water damage.
6 . The computer-implemented method of claim 1 , further comprising:
determining, by the one or more processors, a number of water sensors to place proximate the structure; and
providing, by the one or more processors to the user device, a number of ranked potential sources of water damage which correspond to the number of water sensors to place proximate the structure.
7 . The computer-implemented method of claim 1 , further comprising removing, by the one or more processors, one or more optimal placement locations which do not exist at the structure.
8 . The computer-implemented method of claim 1 , wherein the machine learning model includes a regression model.
9 . The computer-implemented method of claim 1 , wherein the machine learning model includes an algorithm including one or more or k-nearest neighbor, support vector regression, and/or random forest.
10 . The computer-implemented method of claim 1 , wherein the historical water damage claims data indicates one or more of a source of water damage, a cause of the water damage, a location of the water damage, and/or a type of structure where the water damage occurred.
11 . A computer system for determining an optimal placement location of one or more water sensors proximate a structure using machine learning, the system comprising:
one or more processors; and
one or more non-transitory memories storing processor-executable instructions that, when executed by the one or more processors, cause the system to:
obtain structure information for a structure at which the one or more water sensors are to be placed;
provide the structure information to a trained machine learning model to generate an indication of the optimal placement location of the one or more water sensors proximate the structure, wherein:
the trained machine learning model is trained using historical water damage claims data,
the historical water damage claims data includes a geographic location of a structure associated with the corresponding historical water damage claims data,
the trained machine learning model is configured to learn a relationship between building code requirements for the geographic locations and potential sources of water damage, and
the optimal placement location of the one or more water sensors corresponds to the potential sources of water damage; and
provide the indication of the optimal placement location of the one or more water sensors proximate the structure to a user device.
12 . The computer system of claim 11 , wherein the structure information includes data associated with one or more of a floorplan of the structure, structural components of the structure, a property the structure is located upon, plumbing at the structure, and/or appliances at the structure.
13 . The computer system of claim 11 , wherein the structure information includes a geographic location of the property.
14 . The computer system of claim 11 , wherein the machine learning model is further configured to weight one or more attributes of the structure information.
15 . The computer system of claim 11 , wherein the machine learning model is further configured to:
determine a score associated with the potential sources of water damage; and
rank the potential sources of water damage.
16 . The computer system of claim 11 further comprising instructions that, when executed by the one or more processors, cause the system to:
determine a number of water sensors to place proximate the structure; and
provide a number of ranked potential sources of water damage which correspond to the number of water sensors to place proximate the structure to the user device.
17 . The computer system of claim 11 further comprising instructions that, when executed by the one or more processors, cause the system to remove one or more optimal placement locations which do not exist at the property.
18 . The computer system of claim 11 , wherein the machine learning model includes a regression model.
19 . The computer system of claim 11 , wherein the historical water damage claims data indicates one or more of a source of water damage, a cause of the water damage, a location of the water damage, and/or a type of structure where the water damage occurred.
20 . A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to:
obtain structure information for a structure at which one or more water sensors are to be placed;
provide the structure information to a trained machine learning model to generate an indication of an optimal placement location of the one or more water sensors proximate the structure, wherein:
the trained machine learning model is trained using historical water damage claims data,
the historical water damage claims data includes a geographic location of a property associated with the corresponding historical water damage claims data,
the trained machine learning model is configured to learn a relationship between building code requirements for the geographic locations and potential sources of water damage, and
the optimal placement location of the one or more water sensors corresponds to the potential sources of water damage; and
provide the indication of the optimal placement location of the one or more water sensors proximate the structure to a user device.