# US 2023/0274318 A1 · Artificial intelligence machine learning system for classifying images and producing a predetermined visual output

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

- Number: US 2023/0274318 A1
- Document ID: US20230274318A1
- Status: Published application
- Kind: A1
- Application number: 17/683,032
- Filed: 2022-02-28
- Published: 2023-08-31
- Earliest claimed: 2022-02-28
- Assignees: Concat Systems, Inc.
- Inventors: Sudheer Kumar Pamuru
- Web page: https://patentgrep.com/patent/US20230274318A1

## CPC

- G06Q 30/0276: {Advertisement creation}
- G06V 10/82: using neural networks
- G06Q 30/0277: {Online advertisement}
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present disclosure is directed to automatically receiving, modifying, sequencing, and displaying vehicle images for marketing to prospective buyers. A seller uploads images of a vehicle to the system, which system uses artificial intelligence and machine learning to classify the images, identify objects within the images, add backgrounds, banners, and hotspots, and generate metadata associating the results of the foregoing processes with the particular images. The system uses the stored metadata to sequence the images in a format predetermined by the seller and upload the sequenced images for display to a prospective buyer.

## Claims

### Claim 1

At least one computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a computer, causes the computer to perform a method comprising:
receiving a plurality of images, wherein the plurality of images comprises:
a first image comprising at least a first item having a first object;
a second image comprising at least a second item having a second object; and
wherein the first item is different than the second item;
automatically analyzing the first image to identify a first object in the first image as a first identification using artificial intelligence machine learning;
creating a first metadata value associating the first image and the first identification;
automatically using the first object to analyze the first image to classify a first item image within the first image as a first classification using artificial intelligence machine learning;
creating a second metadata value associating the first image and the first classification;
automatically analyzing the second image to identify a second object in the second image as a second identification using artificial intelligence machine learning;
creating a third metadata value associating the second image and the second identification;
automatically using the second object to analyze the second image to classify the second item image within the second image as a second classification using artificial intelligence machine learning;
creating a fourth metadata value associating the second image and a second classification;
receiving a predetermined instruction from a user relating to a preferred display sequence of the first image and the second image; and
using the second metadata value and the fourth metadata value to automatically arrange and display the first modified image and the second modified image in a sequence associated with the preferred display sequence.

### Claim 2 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically analyzing the first image to determine a first location of a first foreground in the first image using artificial intelligence machine learning;
creating a fifth metadata value associating the first image and the first location;
automatically using the fifth metadata value and the first image to create a first modified image having a relocated first foreground and a predetermined background;
automatically analyzing the second image to determine a second location of a second foreground in the second item using artificial intelligence machine learning;
creating a sixth metadata value associating the second image and the second location; and
automatically using the sixth metadata value and the second image to create a second modified image having a relocated second foreground and the predetermined background.

### Claim 3 (depends on 2)

The at least one computer-readable storage medium of claim 2, further comprising associating a hotspot with the first object.

### Claim 4 (depends on 2)

The at least one computer-readable storage medium of claim 2, wherein automatically using the fifth metadata value and the first image to create a first modified image having a relocated first foreground and a predetermined background further comprises;
wherein the first foreground is the first item;
automatically identifying an X coordinate associated with the first item;
automatically identifying a Y coordinate associated with the first item;
automatically using the X coordinate and the Y coordinate to relocate the first item within the first modified image;
automatically resizing the item within the first modified image to position the item within a predefined size parameter associated with the first classification.

### Claim 5 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically identifying a subitem within the first item using artificial intelligence machine learning;
automatically cropping the subitem from the first item to create a cropped subimage;
creating a fifth metadata value associating the subitem and the cropped subimage;
automatically using the fifth metadata value and the cropped subimage to create a modified subimage having a modified background;
using the first metadata value, the fourth metadata value, and the seventh metadata value to automatically arrange the first modified image, the second modified image, and the modified subitem image and produce the user-identifiable output associated with the predetermined instruction. using the second metadata value, the fourth metadata value, and the fifth metadata value to automatically arrange and display the first modified image, the second modified image, and the modified subimage in a sequence associated with the preferred display sequence.

### Claim 6 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically analyzing a first predetermined area of the first image for the existence of a conflict image, using artificial intelligence machine learning;
automatically, in response to identification of a conflict image in the first predetermined area of the first image, adding an overlay to a second predetermined area of the first image using artificial intelligence machine learning; and
wherein the first modified image comprises the overlay in the second predetermined area of the first image.

### Claim 7 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically upscaling the first item into an upscaled item using artificial intelligence machine learning; and
wherein the first modified image comprises the upscaled item.

### Claim 8 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically analyzing the first image to identify a third object in the first image as a third identification using artificial intelligence machine learning;
creating a fifth metadata value associating the first image and the third identification; and
automatically using the fifth metadata value to remove the third object from the first modified image using artificial intelligence machine learning.

### Claim 9 (depends on 8)

The at least one computer-readable storage medium of claim 8 wherein the third object is an image of a license plate.

### Claim 10 (depends on 8)

The at least one computer-readable storage medium of claim 8 wherein the third object is an image of a sticker.

### Claim 11 (depends on 1)

The at least one computer-readable storage medium of claim 1 which, when executed by a computer, further causes the computer to perform the method comprising:
automatically analyzing the first metadata value and the second metadata value to identify a missing image based upon the predetermined instruction; and
automatically displaying an alert identifying the missing image.

### Claim 12

At least one computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a computer, causes the computer to perform a method comprising:
receiving a plurality of images, wherein the plurality of images comprises:
a first image of at least a first item having a first object;
a second image of at least a second item having a second object; and
wherein the first item is different than the second item;
automatically analyzing the first image to locate the first item within the first image as a first location using artificial intelligence machine learning;
automatically analyzing the first image to identify the first object in the first image as a first identification using artificial intelligence machine learning;
automatically using the first object to classify the first image as a first classification using artificial intelligence machine learning;
creating a first metadata value associating the first image and the first location;
creating a second metadata value associating the first image and the first identification;
creating a third metadata value associating the first image and the first classification;
automatically using the first image and the first metadata value to create a first modified image having a modified background;
automatically using the first image and the second metadata value to associate a first hotspot with the second modified image;
automatically analyzing the second image to locate the second item within the second image as a second location using artificial intelligence machine learning;
automatically analyzing the second image to identify the second object in the second image as a second identification using artificial intelligence machine learning;
automatically using the second object to classify the second image as a second classification using artificial intelligence machine learning;
creating a fourth metadata value associating the second image and the second location;
creating a fifth metadata value associating the second image and the second identification;
creating a sixth metadata value associating the second image and the second classification;
automatically using the second image and the fourth metadata value to create a second modified image having a modified background;
automatically using the second image and the fifth metadata value to associate a second hotspot with the second modified image;
receiving a predetermined instruction from a user relating to display of the first image and the second image; and
using the third metadata value and the sixth metadata value to automatically arrange and display the first modified image and the second modified image in a visually-identifiable sequence associated with the predetermined instruction.

### Claim 13 (depends on 12)

The at least one computer-readable storage medium of claim 12, wherein the visually-identifiable sequence is a display of the first modified image and the second modified image in a sequence associated with the predetermined instruction.

### Claim 14 (depends on 12)

The at least one computer-readable storage medium of claim 12, wherein the item is a vehicle and wherein the first object is a feature of the vehicle.

### Claim 15 (depends on 12)

The at least one computer-readable storage medium of claim 12 which, when executed by a computer, causes the computer to perform the method further comprising:
automatically analyzing the first image to identify a third object in the first image as a first identification using artificial intelligence machine learning; and
automatically removing the third object from the first image using artificial intelligence machine learning.

### Claim 16

At least one computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a computer, causes the computer to perform a method comprising:
receiving a plurality of images, wherein the plurality of images comprises:
a first image of a first rotational orientation of a first item;
a second image of a second rotational orientation of the first item;
wherein the first rotational orientation is different than the second rotational orientation;
enabling a user to select a predetermined instruction to input of the first image and the second image;
automatically analyzing the first image to identify a first object in the first image using artificial intelligence machine learning;
automatically creating a first metadata value associated with the first object in the first image and associating the first metadata value with the first image;
automatically analyzing the second image to identify a second object in the second image using artificial intelligence machine learning;
automatically creating a second metadata value associated with the second object in the second image and associating the second metadata value with the second image;
automatically using the first metadata value and the second metadata value to automatically produce a user-identifiable output associated with the predetermined instruction.

### Claim 17 (depends on 16)

The at least one computer-readable storage medium of claim 16, wherein the item is a vehicle and wherein the first object is a feature of the vehicle.

### Claim 18 (depends on 16)

The at least one computer-readable storage medium of claim 16, wherein the user-identifiable output is a display of a first modified image created from upscaling the first image using artificial intelligence machine learning and a second modified image created from upscaling the second image using artificial intelligence machine learning, and wherein the user-identifiable output is a predetermined sequence of the first modified image and the second modified image.

### Claim 19 (depends on 18)

The at least one computer-readable storage medium of claim 18 which, when executed by a computer, further causes the computer to perform the method comprising:
automatically analyzing the first image to identify a first background surrounding the first item in the first image;
automatically removing the first background from the first image;
automatically replacing the first background from the first image with a second background; and
wherein the first modified image comprises the second background.

### Claim 20 (depends on 19)

The at least one computer-readable storage medium of claim 19 wherein the first modified image comprises the first item relocated within the first image using artificial intelligence machine learning.
