# US 2018/0018729 A1 · Systems, methods, and computer program products for intelligently processing and manipulating a subject image according to consumer data

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

- Number: US 2018/0018729 A1
- Document ID: US20180018729A1
- Status: Published application
- Kind: A1
- Application number: 15/647,721
- Filed: 2017-07-12
- Published: 2018-01-18
- Earliest claimed: 2016-07-12
- Assignees: United Parcel Service of America, Inc.
- Applicants: United Parcel Service of America, Inc.
- Inventors: Jessica Grimes
- Web page: https://patentgrep.com/patent/US20180018729A1

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06Q 30/0255: {based on user history}
- G06Q 30/0261: {based on user location}
- G06Q 30/0643: {graphically representing goods, e.g. 3D product representation}
- 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 system, method and computer program product are provided for processing a subject image, consumer data, and product images to generate product recommendations. Subject images may be provided by consumers and may include products they wish to buy, and/or images of themselves to be utilized as an avatar. The subject image, and other images provided by other consumers may be processed to determine image characteristics, and correlations with consumer data including preferences, demographics, style preferences, physical characteristics, and/or the like. Trends, styles, and preferences may be intelligently learned such that relevant products are provided to a consumer. The subject image may be manipulated, such as by dressing an avatar in a recommended clothing article, and/or the like.

## Claims

### Claim 1

A system for processing a subject image, consumer data and product images to generate product recommendations, the system comprising:
at least one processor; and
at least one memory device for storing (a) images received from consumers, (b) the consumer data relating to at least one of consumer preferences, consumer purchase history or consumer browsing history, and (c) the product images received from third parties;
wherein the at least one processor of the system is configured to:
receive the subject image associated with a subject consumer;
perform electronic image processing of the subject image to determine at least one image characteristic therein;
identify a subset of images accessed from the stored images received from consumers, wherein the subset of images each comprise the at least one image characteristic;
access a subset of the consumer data identified as being associated with the subset of images comprising the at least one image characteristic;
determine data-image correlations between the consumer data and respective images of the subset of images comprising the at least one image characteristic;
generate image characteristics describing product images received from the third parties by electronic image processing;
apply the determined data-image correlations to the generated image characteristics to identify particular consumer-relevant product images received from the third parties; and
generate electronic instructions that automatically generate, in a consumer interface, the product recommendations for the subject consumer.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one processor is further configured to:
predictively adjust consumer data associated with the subject consumer based on correlations of other consumer data and respective associated images, wherein the product recommendations are further generated based on the predictively adjusted consumer data.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one processor is further configured to:
determine position data associated with the subject image;
manipulate the subject image with at least one product image associated with at least one product recommendation, wherein the product image is incorporated into the subject image according to the determined position data; and
cause provision of the manipulated subject image on a user computing entity.

### Claim 4 (depends on 1)

The system of claim 1, wherein the at least one processor is further configured to:
via the consumer interface, enable consumer directed manipulation of the subject image with at least one product image associated with at least one product recommendation.

### Claim 5 (depends on 1)

The system of claim 1, wherein the at least one processor is further configured to:
generate a natural language query to solicit additional information regarding preferences of the subject consumer; and
process a received natural language response to generate consumer preferences, wherein the product recommendations are further based on the generated consumer preferences.

### Claim 6 (depends on 1)

The system of claim 1, wherein the at least one processor is further configured to:
predictively determine a shipping preference for a selected product recommendation based on at least one of the consumer data or the at least one image characteristic.

### Claim 7 (depends on 1)

The system of claim 1, wherein the at least one memory device further stores (d) interaction data describing consumer interactions with electronic advertisements, and the processor is further configured to:
process the interaction data to determine a targeted advertisement for the subject consumer and the generated product recommendations.

### Claim 8 (depends on 1)

The system of claim 1, wherein the subject image is received via an external consumer-facing third party system.

### Claim 9 (depends on 1)

The system of claim 1, wherein the subject image is received via the consumer interface communicatively connected to the system via at least one network.

### Claim 10

A computer-implemented method for processing a subject image, consumer data and product images to generate product recommendations, the method comprising:
receiving and storing within one or more memory storage areas of a system, (a) images received from consumers, (b) the consumer data relating to at least one of consumer preferences, consumer purchase history or consumer browsing history, and (c) the product images received from third parties;
receiving the subject image associated with a subject consumer;
performing electronic image processing of the subject image to determine at least one image characteristic therein;
identifying a subset of images accessed from the stored images received from consumers, wherein the subset of images each comprise the at least one image characteristic;
accessing a subset of the consumer data identified as being associated with the subset of images comprising the at least one image characteristic;
determining data-image correlations between the consumer data and respective images of the subset of images comprising the at least one image characteristic;
generating image characteristics describing product images received from the third parties by electronic image processing;
applying the determined data-image correlations to the generated image characteristics to identify particular consumer-relevant product images received from the third parties; and
generating electronic instructions that automatically generate, in a consumer interface, the product recommendations for the subject consumer.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, further comprising:
predictively adjusting consumer data associated with the subject consumer based on correlations of other consumer data and respective associated images, wherein the product recommendations are further generated based on the predictively adjusted consumer data.

### Claim 12 (depends on 10)

The computer-implemented method of claim 10, further comprising:
determining position data associated with the subject image;
manipulating the subject image with at least one product image associated with at least one product recommendation, wherein the product image is incorporated into the subject image according to the determined position data; and
causing provision of the manipulated subject image on a user computing entity.

### Claim 13 (depends on 10)

The computer-implemented method of claim 10, further comprising:
via the consumer interface, enabling consumer directed manipulation of the subject image with at least one product image associated with at least one product recommendation.

### Claim 14 (depends on 10)

The computer-implemented method of claim 10, further comprising:
generating a natural language query to solicit additional information regarding preferences of the subject consumer; and
processing a received natural language response to generate consumer preferences, wherein the product recommendations are further based on the generated consumer preferences.

### Claim 15 (depends on 10)

The computer-implemented method of claim 10, further comprising:
predictively determining a shipping preference for a selected product recommendation based on at least one of the consumer data or the at least one image characteristic.

### Claim 16 (depends on 10)

The computer-implemented method of claim 10, further comprising:
receiving and storing (d) interaction data describing consumer interactions with electronic advertisements; and
processing the interaction data to determine a targeted advertisement for the subject consumer and the generated product recommendations.

### Claim 17 (depends on 10)

The computer-implemented method of claim 10, wherein the subject image is received via an external consumer-facing third party system.

### Claim 18 (depends on 10)

The computer-implemented method of claim 10, wherein the subject image is received via the consumer interface communicatively connected to the system via at least one network.

### Claim 19

A computer program product for processing a subject image, consumer data and product images to generate product recommendations, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions embodied therein, the computer-readable program code portions comprising one or more executable portions configured for:
receiving and storing within one or more memory storage areas of a system, (a) images received from consumers, (b) the consumer data relating to at least one of consumer preferences, consumer purchase history or consumer browsing history, and (c) the product images received from third parties;
receiving the subject image associated with a subject consumer;
performing electronic image processing of the subject image to determine at least one image characteristic therein;
identifying a subset of images accessed from the stored images received from consumers, wherein the subset of images each comprise the at least one image characteristic;
accessing a subset of the consumer data identified as being associated with the subset of images comprising the at least one image characteristic;
determining data-image correlations between the consumer data and respective images of the subset of images comprising the at least one image characteristic;
generating image characteristics describing product images received from the third parties by electronic image processing;
applying the determined data-image correlations to the generated image characteristics to identify particular consumer-relevant product images received from the third parties; and
generating electronic instructions that automatically generate, in a consumer interface, the product recommendations for the subject consumer.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the computer-readable program code portions further comprise one or more executable portions configured for:
predictively adjusting consumer data associated with the subject consumer based on correlations of other consumer data and respective associated images, wherein the product recommendations are further generated based on the predictively adjusted consumer data.

### Claim 21 (depends on 19)

The computer program product of claim 19, wherein the computer-readable program code portions further comprise one or more executable portions configured for:
determining position data associated with the subject image;
manipulating the subject image with at least one product image associated with at least one product recommendation, wherein the product image is incorporated into the subject image according to the determined position data; and
causing provision of the manipulated subject image on a user computing entity.

### Claim 22 (depends on 19)

The computer program product of claim 19, wherein the computer-readable program code portions further comprise one or more executable portions configured for:
via the consumer interface, enabling consumer directed manipulation of the subject image with at least one product image associated with at least one product recommendation.

### Claim 23 (depends on 19)

The computer program product of claim 19, wherein the computer-readable program code portions further comprise one or more executable portions configured for:
generating a natural language query to solicit additional information regarding preferences of the subject consumer; and
processing a received natural language response to generate consumer preferences, wherein the product recommendations are further based on the generated consumer preferences.
