Dynamic Ad Content Generation Using Style Transfer Networks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current targeted advertising systems cannot dynamically modify image and video content based on user preferences after initial user preference information is determined, requiring pre-made advertisements that do not adapt to changing user preferences.

Innovation Solution

A system and method utilizing a client device, server, and database with generative adversarial networks to dynamically modify content by querying user preference information and applying style transfers to content templates, allowing for real-time adaptation of advertisements based on user preferences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If pre-made advertisements are used for targeted advertising, then the advertising content can be delivered to specific audiences based on user information, but the advertisements cannot be dynamically modified after user preference information is determined

Engineering Contradiction:

Improveadaptability to user preferencesVSAvoidsystem complexity for dynamic modification

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic advertisement generation by allowing the system to modify advertisement content in real-time based on user preferences. Instead of using static pre-made advertisements, the system dynamically adjusts image and video content parameters (such as style, color, composition) according to user profile information retrieved from browser cookies, enabling the advertisement to adapt to each user's specific preferences

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes multiple parameters of the advertisement content simultaneously, including image style parameters, color schemes, composition elements, and video footage selection, all based on user preference data. This allows the advertisement to be customized for different user segments (e.g., cartoon style for children, live-action for adults) by modifying these parameters in response to user information

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If multiple pre-made advertisements are created for different user segments, then the advertising can target specific audiences, but the content cannot be modified after user preference determination

Engineering Contradiction:

Improvereal-time content adaptationVSAvoidtime for content creation and modification

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-collecting and storing user preference information in browser cookies before the advertisement delivery. This allows the system to have user profile data ready in advance, so when an advertisement is to be displayed, the content can be immediately customized based on the pre-stored preferences without delay

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical process of manually creating and managing multiple pre-made advertisements with an automated computational system. The system uses algorithms to retrieve user information, determine preferences, and automatically generate or modify advertisement content, eliminating the need for manual content creation and reducing time loss

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of information

If browser cookies are used to store user information, then targeted advertising can be implemented based on user preferences, but the advertisements must be pre-made and cannot be dynamically modified

Engineering Contradiction:

Improveuser preference information retentionVSAvoiddynamic content generation

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The system implements feedback by continuously retrieving user preference information from browser cookies and using this information to dynamically adjust advertisement content. The feedback loop ensures that the advertisement content remains aligned with user preferences by constantly referencing the stored user information and making real-time modifications based on this feedback

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20240362403A1Systems and methods for generating customized content based on user preferences

Publication Date: 2024.10.31 CAPITAL ONE SERVICES LLC

AI summary

Embodiments disclosed herein provide for dynamically modifying image and/or video content based on user preferences. Embodiments provide a server, a database containing user preference information and one or more content templates, and a content generator comprising a plurality of generative adversarial networks, wherein each generative adversarial network is associated with a corresponding style transfer, and the content generator is configured to apply one or more style transfers to a base image to convert the base image into a desired style. Once created, the customized content is sent to a client device to for display.