# US 2026/0030653 A1 · Systems and methods for generating marketing content attribution and insights

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

- Number: US 2026/0030653 A1
- Document ID: US20260030653A1
- Status: Published application
- Kind: A1
- Application number: 19/279,439
- Filed: 2025-07-24
- Published: 2026-01-29
- Earliest claimed: 2024-07-26
- Assignees: Climate LLC
- Applicants: Climate LLC
- Inventors: Michelle FILLA; Thomas JEAN; Cameron TURNER; John OROZCO; Scott HERMES; Steven VLACH
- Web page: https://patentgrep.com/patent/US20260030653A1

## CPC

- G06Q 30/0242: Determining effectiveness of advertisements
- G06Q 30/0244: {Optimization}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06Q 30/0276: {Advertisement creation}
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods are provided to generate marketing content insights. In one embodiment, a disclosed method includes receiving input data including one or more advertising assets and one or more metrics corresponding to the one or more advertising assets; using a computer vision model, identifying one or more constituent elements of the one or more advertising assets; appending the one or more constituent elements and/or descriptions of the one or more constituent elements to the input data to generate a structured data set; training a generative AI model using the structured data set; training a prediction model using the structured data set; based on the trained generative AI model and a prompt, generating an additional advertising asset not included in the one or more advertising assets; and based on the trained prediction model, generating at least one predicted metric of the additional advertising asset.

## Claims

### Claim 1

A method for generating marketing content insights, comprising:
receiving input data including one or more advertising assets and one or more metrics corresponding to the one or more advertising assets;
using a computer vision model, identifying one or more constituent elements of the one or more advertising assets;
appending the one or more constituent elements and/or descriptions of the one or more constituent elements to the input data to generate a structured data set;
training a generative AI model using the structured data set;
training a prediction model using the structured data set;
based on the trained generative AI model and a prompt, generating an additional advertising asset not included in the one or more advertising assets; and
based on the trained prediction model, generating at least one predicted metric of the additional advertising asset.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more metrics corresponding to the one or more advertising assets includes at least one of:
a number of comments on each of the one or more advertising assets;
a number of times each of the one or more advertising assets was shared;
a number of impressions made by each of the one or more advertising assets;
a channel of each of the one or more advertising assets;
a number of times each of the one or more advertising assets was liked;
a number of times each of the one or more advertising assets was clicked upon;
a country corresponding to each of the one or more advertising assets;
a click-through-rate for each of the one or more advertising assets;
a media type of each of the one or more advertising assets;
a media Uniform Resource Locator (URL) of each of the one or more advertising assets; and
a start date of each of the one or more advertising assets.

### Claim 3 (depends on 2)

The method of claim 2, wherein the structured data set further comprises at least one of:
a response field containing, for each of the one or more advertising assets, a summation of the number of comments, the number of shares, the number of likes, and the number of clicks; and
a response rate field containing, for each of the one or more advertising assets, the response divided by the number of impressions.

### Claim 4 (depends on 1)

The method of claim 1, wherein the one or more constituent elements includes at least one of:
a call-to-action (CTA) of each of the one or more advertising assets;
a headline of each of the one or more advertising assets;
objects recognized in each of the one or more advertising assets by the computer vision model;
colors recognized in each of the one or more advertising assets by the computer vision model;
a tone recognized in each of the one or more advertising assets by the computer vision model;
a summary of each of the one or more advertising assets; and
text recognized in each of the one or more advertising assets by the computer vision model.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
using a natural language processing (NLP) module, generating a list of Top N objects across the one or more advertising assets;
filtering the objects identified in each of the one or more advertising assets against the list of Top N objects;
generating vectors corresponding to the filtered objects for each of the one or more advertising assets; and
appending the vectors to the structured data set.

### Claim 6 (depends on 5)

The method of claim 5, wherein the NLP module is implemented using Azure™ services, BERT, ROBERTa, or GPT™.

### Claim 7 (depends on 1)

The method of claim 1, wherein when the one or more advertising assets includes emails, the one or more metrics corresponding to the one or more advertising assets includes at least one of:
a name of an email campaign;
a subject of the emails;
a number of emails sent;
a number of emails delivered;
a delivery rate of the emails;
a number of times the emails were opened; and
an open rate of the emails.

### Claim 8 (depends on 1)

The method of claim 1, wherein the computer vision model identifies the one or more constituent elements in response to a series of prompts entered into the computer vision model by a user.

### Claim 9 (depends on 1)

The method of claim 1, wherein when the one or more advertising assets includes a Graphics Interchange Format (gif) file, the method further comprises:
comparing a frame in the gif file with a successive frame; and
discarding the successive frame when the frame and the successive frame are insufficiently different.

### Claim 10 (depends on 1)

The method of claim 1, wherein the computer vision model is implemented using GPT-4V™, DALL-E™, and/or Azure™ AI Vision.

### Claim 11

A system for generating marketing content insights, comprising:
at least one processor;
a display communicatively coupled to the at least one processor and configured to display a result based on computations performed by the at least one processor; and
a memory communicatively coupled to the at least one processor, the memory storing executable instructions, which when executed by the at least one processor, cause the at least one processor to:
receive input data including one or more advertising assets and one or more metrics corresponding to the one or more advertising assets;
using a computer vision model, identify one or more constituent elements of the one or more advertising assets;
append the one or more constituent elements and/or descriptions of the one or more constituent elements to the input data to generate a structured data set;
train a generative AI model using the structured data set;
train a prediction model using the structured data set;
based on the trained generative AI model and a prompt, generate an additional advertising asset not included in the one or more advertising assets and displaying the additional advertising asset on the display; and
based on the trained prediction model, generate at least one predicted metric of the additional advertising asset.

### Claim 12 (depends on 11)

The system of claim 11, wherein the one or more metrics corresponding to the one or more advertising assets includes at least one of:
a number of comments on each of the one or more advertising assets;
a number of times each of the one or more advertising assets was shared;
a number of impressions made by each of the one or more advertising assets;
a channel of each of the one or more advertising assets;
a number of times each of the one or more advertising assets was liked;
a number of times each of the one or more advertising assets was clicked upon;
a country corresponding to each of the one or more advertising assets;
a click-through-rate for each of the one or more advertising assets;
a media type of each of the one or more advertising assets;
a media Uniform Resource Locator (URL) of each of the one or more advertising assets; and
a start date of each of the one or more advertising assets.

### Claim 13 (depends on 12)

The system of claim 12, wherein the structured data set further comprises at least one of:
a response field containing, for each of the one or more advertising assets, a summation of the number of comments, the number of shares, the number of likes, and the number of clicks; and
a response rate field containing, for each of the one or more advertising assets, the response divided by the number of impressions.

### Claim 14 (depends on 11)

The system of claim 11, wherein the one or more constituent elements includes at least one of:
a call-to-action (CTA) of each of the one or more advertising assets;
a headline of each of the one or more advertising assets;
objects recognized in each of the one or more advertising assets by the computer vision model;
colors recognized in each of the one or more advertising assets by the computer vision model;
a tone recognized in each of the one or more advertising assets by the computer vision model;
a summary of each of the one or more advertising assets; and
text recognized in each of the one or more advertising assets by the computer vision model.

### Claim 15 (depends on 14)

The system of claim 14, wherein the memory stores further executable instructions that cause the at least one processor to:
using a natural language processing (NLP) module, generate a list of Top N objects across the one or more advertising assets;
filter the objects identified in each of the one or more advertising assets against the list of Top N objects;
generate vectors corresponding to the filtered objects for each of the one or more advertising assets; and
append the vectors to the structured data set.

### Claim 16 (depends on 15)

The system of claim 15, wherein the NLP module is implemented using Azure™ services, BERT, ROBERTa, or GPT™.

### Claim 17 (depends on 11)

The system of claim 11, wherein when the one or more advertising assets includes emails, the one or more metrics corresponding to the one or more advertising assets includes at least one of:
a name of an email campaign;
a subject of the emails;
a number of emails sent;
a number of emails delivered;
a delivery rate of the emails;
a number of times the emails were opened; and
an open rate of the emails.

### Claim 18 (depends on 11)

The system of claim 11, wherein the computer vision model identifies the one or more constituent elements in response to a series of prompts entered into the computer vision model by a user.

### Claim 19 (depends on 11)

The system of claim 11, wherein when the one or more advertising assets includes a Graphics Interchange Format (gif) file, the memory stores further executable instructions that cause the at least one processor to:
compare a frame in the gif file with a successive frame; and
discard the successive frame when the frame and the successive frame are insufficiently different.

### Claim 20 (depends on 11)

The system of claim 11, wherein the computer vision model is implemented using GPT-4V™, DALL-E™, and/or Azure™ AI Vision.
