# US 2024/0404250 A1 · Method and system for inventorying and developing the value of real property

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

- Number: US 2024/0404250 A1
- Document ID: US20240404250A1
- Status: Published application
- Kind: A1
- Application number: 18/800,234
- Filed: 2024-08-12
- Published: 2024-12-05
- Earliest claimed: 2021-11-04
- Inventors: David M. Barnett
- Web page: https://patentgrep.com/patent/US20240404250A1

## CPC

- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06Q 30/0278: {Product appraisal}
- G06Q 50/16: Real estate
- G06V 20/176: {Urban or other man-made structures}
- G06V 2201/10: Recognition assisted with metadata
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method and system of inventorying and developing value for real property. An image or an aerial photograph of a property to be inventoried and valued is obtained, an outline or outlines of the structure and its location on the property are identified, outlines of the structural sections of the property are mapped, a partial sketch of the outline of the structure is created, wherein the outline includes square footage estimates for each section, and is oriented with the front of the structure to the bottom of the page, and the information is integrated across multiple images and the structural type of each section of the structure is identified. The method and system rely on machine learning in order to increase the accuracy of the method and system.

## Claims

### Claim 1

A computer-generated method comprising:
receiving, by a server or a processor, geographic information system layer input that includes parcel data;
responsive to receiving the parcel data, the server or the processor initiates fetch logic to request aerial imagery from an imagery API;
responsive to receiving the aerial imagery, the server or the processor overlays the geographic information system layer onto the aerial imagery generating a superimposed layer;
receiving, by a computer vision model from the server or processor, the superimposed layer and a building dataset;
responsive to receiving the superimposed layer and the building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer;
receiving, by the server or the processor, the segmentation layer, the boundary layer, and the perimeter layer,
receiving, by a sketch extraction model, the segmentation layer, the boundary layer, and the perimeter layer;
responsive to receiving a segmentation layer, a boundary layer, and a perimeter layer, the sketch extraction model uses sketch logic to generate a sketch layer;
receiving, by the server or the processor, the sketch layer;
receiving, by a second computer vision model, the sketch layer;
responsive to receiving the sketch layer, second computer vision model initiates a second vision logic, which generates a floor layer;
receiving, by a server or processor, the floor layer; and,
responsive to receiving the floor layer, the server or the processor initials optimizing logic, which generates an optimized layer.

### Claim 2 (depends on 1)

The computer-generated method of claim 1, wherein the parcel data is provided by a municipality.

### Claim 3 (depends on 1)

The computer-generated method of claim 1, wherein the computer vision model is a machine learning platform.

### Claim 4 (depends on 3)

The computer-generated method of claim 3, wherein the step of responsive to receiving the superimposed layer and building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer may be iterative and may be performed at least two times.

### Claim 5

A computer-generated method comprising:
receiving, by a server or a processor, geographic information system layer input that includes parcel data;
responsive to receiving the parcel data, the server or the processor initiates fetch logic to request imagery from a property record card from an imagery API;
responsive to receiving the imagery, the the server or the processor overlays the geographic information system layer onto the aerial imagery generating a superimposed layer;
receiving, by a computer vision model from the server or the processor, the superimposed layer and a building dataset;
responsive to receiving the superimposed layer and the building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer;
receiving, by the server or the processor, the segmentation layer, the boundary layer, and the perimeter layer,
receiving, by a sketch extraction model, the segmentation layer, the boundary layer, and the perimeter layer;
responsive to receiving the segmentation layer, the boundary layer, and the perimeter layer, sketch extraction model uses sketch logic to generate a sketch layer;
receiving, by the server or the processor, the sketch layer;
receiving, by a second computer vision model, the sketch layer;
responsive to receiving the sketch layer, the second computer vision model initiates a second vision logic, which generates a floor layer;
receiving, by the server or the processor, the floor layer; and,
responsive to receiving the floor layer, the server or the processor initials optimizing logic, which generates an optimized layer.

### Claim 6 (depends on 5)

The computer-generated method of claim 5, wherein the parcel data is provided by a municipality.

### Claim 7 (depends on 5)

The computer-generated method of claim 5, wherein the computer vision model is a machine learning platform.

### Claim 8 (depends on 7)

The computer-generated method of claim 7, wherein the step of responsive to receiving the superimposed layer and the building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer may be iterative and may be performed at least two times.

### Claim 9

A computer-generated method comprising:
receiving, by a server or a processor, geographic information system layer input that includes parcel data;
responsive to receiving the parcel data, the server or the processor initiates fetch logic to request imagery from an imagery API;
responsive to receiving the imagery, the the server or the processor overlays the geographic information system layer onto the aerial imagery generating a superimposed layer;
receiving, by a computer vision model from the server or the processor, the superimposed layer and a building dataset;
responsive to receiving the superimposed layer and the building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer;
receiving, by the server or the processor, the segmentation layer, the boundary layer, and the perimeter layer,
receiving, by a sketch extraction model, the segmentation layer, the boundary layer, and the perimeter layer;
responsive to receiving the segmentation layer, the boundary layer, and the perimeter layer, sketch extraction model uses sketch logic to generate a sketch layer; and,
receiving, by the server or the processor, the sketch layer.

### Claim 10 (depends on 9)

The computer-generated method of claim 9, wherein the parcel data is provided by a municipality.

### Claim 11 (depends on 9)

The computer-generated method of claim 9, wherein the computer vision model is a machine learning platform.

### Claim 12 (depends on 11)

The computer-generated method of claim 11, wherein the step of responsive to receiving the superimposed layer and the building dataset, the computer vision model initiates a vision logic, which generates a segmentation layer, a boundary layer, and a perimeter layer may be iterative and may be performed at least two times.
