ad campaign management engine

Abstract

This paper describes a method, system, and computer storage medium for providing an advertising campaign management engine within an artificial intelligence system. Advertising campaign management refers to the process of planning, executing, monitoring, and optimizing advertising campaigns. Operationally, it first involves high-conversion design modeling and mining analysis of performance data and user preferences to identify design elements (such as image style and text layout) that enhance engagement. Next, design requirement generation transforms ad optimization profiles into structured prompts that guide the refinement of ad design. Finally, design fine-tuning utilizes advanced generative models to adjust ad elements (such as images and layout) based on generated requirements. The advertising campaign management engine supports an iterative process that enables automatic updates and optimization, allowing ads to be customized based on specific demographics. For example, it can create unique designs for young people or simplified layouts for older people. The refined ads are then deployed and continuously monitored for performance improvement.

Description

Technical Field

[0001] Embodiments of this application relate to the field of computing, and more specifically to artificial intelligence systems, particularly to generative artificial intelligence knowledge graph engines in item listing systems. Background Technology

[0002] Users can interact with generative artificial intelligence (AI) technologies across various applications and services to complete computational tasks. Generative AI refers to a class of AI systems and algorithms designed to generate new data or content that is similar to, or in some cases completely different from, the data on which they were trained. Generative AI systems can create text, image, music and audio, video, and data synthesis. Specifically, generative AI systems can support item listing systems in several ways to improve operational efficiency, customer engagement, and online shopping. For example, item listing systems can utilize generative AI systems for content generation (e.g., product descriptions), personalized shopping experiences (e.g., recommendation engines), product discovery (e.g., visual search), and security management (e.g., fraud detection). Item listing systems can leverage generative AI to enhance their functionality through application programming interfaces (APIs), pre-trained models, and custom AI solutions. Summary of the Invention

[0003] The various aspects of the technology described herein generally relate to systems, methods, and computer storage media for providing advertising campaign management, etc., using an advertising campaign management engine within an artificial intelligence system. Advertising campaign management refers to the process of planning, executing, monitoring, and optimizing advertising campaigns to achieve specific business objectives. Advertising campaign management involves targeting the right audience, selecting appropriate ad formats, tracking performance metrics, and making data-driven adjustments to maximize engagement, conversion rates, and ROI. The advertising campaign management engine in this technical solution integrates historical and real-time performance data to dynamically refine ad design.

[0004] The campaign management engine comprises three main components. First, it performs high-conversion design modeling and mines user preferences to identify design elements that drive engagement (e.g., image style and text layout). Second, design requirement generation transforms user profiles or user group profiles into structured prompts that guide the refinement of ad design. Finally, design fine-tuning utilizes advanced generative models to adjust ad elements (e.g., images and layout) based on the generated requirements. The campaign management engine supports an iterative process capable of automatic updates and optimization, allowing ads to be tailored to specific demographics. For example, it can create unique designs for young people or simplified layouts for older people. The refined ads are then deployed and continuously monitored to improve performance. The benefits of this approach include providing users with a personalized and relevant ad experience, improving conversion rates through real-time adjustments, reducing manual and delayed automatic refinement, and providing scalability to adapt to changing market demands and user preferences.

[0005] Operationally, the campaign management engine optimizes campaigns by leveraging historical data, user feedback, and advanced generative models. This process begins with collecting campaign data, such as designing performance metrics (clicks, conversion rates) and / or user feedback (explicit surveys or implicit engagement). This data is used to identify patterns and guide ad refinement.

[0006] Offline data mining analyzes ad design performance data to understand which layouts, text styles, and images generate high engagement. User feedback is mined to uncover audience preferences; for example, older audiences prefer detailed descriptions and large fonts, while younger users favor minimalist designs. This data helps train ad optimization models to identify factors influencing ad layout and content, as well as image processing preferences for different demographic segments. Using the ad optimization model and ad campaigns, ad optimization profiles for the campaigns can be generated.

[0007] Conditional text template generators use these insights (i.e., ad optimization profiles) to recommend tweaks for ad layouts and images. For example, an ad targeting middle-aged professionals might have a bold, dark blue headline, while an ad targeting a younger audience could emphasize a striking image with minimal text. Advertisers provide the original campaign elements, such as text and images, and the system makes custom adjustments. Design requirements generators are used to generate fine-tuning tips for ad campaigns.

[0008] Generative models are used to create the final ads. For example, a multimodal ad layout generation model ensures consistent text and visual arrangement, while an ad image processing model adjusts visual elements such as brightness and color balance. The refined ads are deployed, and their performance is continuously monitored. If performance is suboptimal, the campaign management engine iterates by trying adjustments to improve engagement. By automating the ad refinement process, the campaign management engine creates personalized and relevant ads, simplifying campaign management while reducing manual intervention. Its scalability and adaptability ensure its effectiveness in dynamic advertising environments.

[0009] This summary is provided to introduce, in a simplified form, the selection of concepts further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to help define the scope of the claimed subject matter. Attached Figure Description

[0010] The technology described herein is described in detail below with reference to the accompanying drawings, in which:

[0011] Figures 1A to 1D This is a schematic diagram of an artificial intelligence system for providing advertising campaign management in an item listing system, based on the technical aspects described in this article;

[0012] Figure 2A This is a block diagram of an artificial intelligence system for providing advertising campaign management in an item listing system, based on the technical aspects described in this article;

[0013] Figure 2B This is a flowchart of an artificial intelligence system for providing advertising campaign management in an item listing system, based on the technical aspects described herein;

[0014] Figure 3 This provides a first exemplary method for providing advertising campaign management in an item list system based on the technical aspects described herein;

[0015] Figure 4 A second exemplary method for providing advertising campaign management in an item list system based on the technical aspects described herein is provided;

[0016] Figure 5 A third exemplary method for providing advertising campaign management in an item list system based on the technical aspects described herein is provided;

[0017] Figure 6 A block diagram of a list of exemplary project systems suitable for implementing the techniques described herein is provided;

[0018] Figure 7Block diagrams are provided that are suitable for implementing the techniques described herein; and

[0019] Figure 8 This is a block diagram of an exemplary computing environment suitable for implementing the techniques described herein. Detailed Implementation

[0020] Overview

[0021] The project listing system and platform support storing projects (products or assets) in a project database and provides a search system for receiving queries and identifying search result projects based on those queries. A project (e.g., a physical project or a digital project) refers to a product or asset offered for listing on the project listing platform. The search system supports identifying result projects from the project database in response to a received query. The project database can be dedicated to a content platform or a project listing platform, such as the eBay content platform developed by eBay Inc. of San Jose, California. The project listing system can also provide generative AI-enabled applications (“generative AI applications”) that utilize generative AI models (e.g., large language models—“LLM”) to create, generate, or produce content, data, or output. LLM is a specific category of generative AI models that primarily focus on generating human-like text. Generative AI models (such as GPT (Generative Pre-trained Transformer) and its variants) are designed to generate human-like text or other types of data based on inputs they receive (e.g., via prompting interfaces). These applications use generative AI to perform a variety of tasks across different domains to provide improvements in automation, efficiency, and human-like interaction.

[0022] Digital platforms that enable advertising can include online services or websites that allow businesses or individuals to promote their products, services, or content to a target audience. These platforms rely on a complex infrastructure of technologies that enable the delivery, targeting, and measurement of advertising. At the heart of these platforms are ad servers, which store, manage, and deliver ads to users. These servers process requests from websites or applications, matching them with appropriate ads based on targeting criteria and serving them in real time. Ad servers also track key performance metrics such as impressions, clicks, and conversion rates, which are crucial for reporting and analytics.

[0023] Digital platforms typically collect vast amounts of data about user behavior, demographics, and interactions through cookies, pixels, or device identifiers. This data is processed to create user profiles, which are then used to segment audiences for more precise targeting. Targeting mechanisms can include contextual targeting based on what the user is viewing, demographic targeting such as age or location, behavioral targeting based on past actions, and retargeting based on users who have previously interacted with the ad. All of these are designed to ensure the right ad reaches the right user at the right time.

[0024] To measure advertising effectiveness, digital platforms employ sophisticated tracking and analytics systems. Metrics such as impressions, clicks, conversion rates, and return on ad spend (ROAS) are captured in real time, allowing advertisers to evaluate the performance of their campaigns. Machine learning algorithms further optimize these campaigns by analyzing user interactions and adjusting ad delivery to improve engagement and conversion rates.

[0025] In addition, many platforms offer APIs (Application Programming Interfaces) and SDKs (Software Development Kits), which allow advertisers and third-party tools to integrate with the platform. These integrations enable the automation of ad creation, management, and reporting, as well as the ability to embed ads within external websites and applications. In short, these technological components create a seamless, dynamic ecosystem that enables advertisers to reach highly targeted audiences, optimize ad performance, and track the success of their campaigns in real time.

[0026] Traditionally, digital platforms lack the comprehensive computing logic and infrastructure to effectively fine-tune ad campaigns based on ad design and performance data. Typically, campaigns are managed by the digital platform (e.g., search engines, e-commerce websites, or listing services), while campaign design is handled by the seller or a third-party design firm. Consequently, performance data from campaigns cannot be automatically or seamlessly used to refine ad design features. Campaigns enable sellers to accurately identify and reach their target audiences (e.g., specific users or user groups). These campaigns consist of one or more ads targeting the target audience. However, even for precisely defined target audiences, campaign performance can be influenced by ad design features. It is worth noting that certain performance metrics (e.g., conversion rates) can vary significantly across different target audiences.

[0027] For example, an e-commerce platform runs an advertising campaign for sellers (advertisers) promoting a new shoe collection. The campaign targets two distinct groups: fashion-conscious young adults aged 18 to 25 and comfort-conscious middle-aged adults aged 35 to 50. While the ad may perfectly target each group, the results could be vastly different. For the younger audience, the ad's trendy, fashionable designs, bold visuals, and strong emphasis on style would likely resonate well, resulting in higher conversion rates. However, for the older group, the same ad might perform poorly. They might prefer designs that emphasize comfort, durability, and functionality, leading to lower conversion rates for that group.

[0028] This performance disparity illustrates a core challenge: fine-tuning ad design during campaigns. While e-commerce platforms may collect conversion rate data (e.g., clicks and purchases per group), the process of adjusting designs based on that data is often fragmented. The e-commerce platform manages the campaign, but ad design is typically created by the seller or a third-party agency. This division can make it difficult to quickly adjust ad design based on performance insights. If conversion rates are lower for older user groups, for example, the platform's data isn't always directly correlated with the design team's ability to modify ads in real time, slowing down the optimization process. Therefore, even for precise targeting, campaign success still largely depends on how well the ads resonate with the unique preferences of each user group and how effectively the design can be adjusted based on performance data. Thus, a more comprehensive item list system (with an alternative foundation providing ad management functionality) can improve the computational operations and interface of ad management.

[0029] Description of the technical solution

[0030] At a high level, the campaign management engine implements a technical solution designed to optimize campaigns by dynamically refining ad design based on performance data and user preferences. By leveraging data analytics, machine learning, and generative models, the campaign management engine improves ad performance in real time, acting as an end-to-end solution that automates and simplifies the entire campaign optimization process.

[0031] Operationally, the campaign management engine uses historical ad design performance data to identify ad design patterns that drive user engagement and conversion rates, focusing on user preferences rather than traditional demographic segmentation. Through advanced methods such as clustering and feature analysis, the campaign management engine defines distinct user groups and links their profiles to specific design elements (e.g., image style, text layout, and localization). Specifically, the ad optimization model is generated based on modeling relationships between user groups, preference features, and preference links. This model personalizes ad content to match the unique tastes and expectations of each audience segment.

[0032] To translate these insights into actionable outputs, the campaign management engine processes ad optimization profiles associated with user profiles or user group profiles for the campaign, as well as a design requirement generator, to produce structured design tips in formats such as JSON. These outputs specify necessary adjustments to ad elements—from image style and text targeting to other fine-tuned design requirements—to resonate with different user groups.

[0033] Refinement is performed using generative models, such as design fine-tuning models and multimodal generative models, which can adjust visual and text ad components. Tools such as image diffusion models ensure stylistic consistency, while layout generators provide precise placement of text and objects, ensuring updates perfectly match specified preferences. This automation ensures consistent, personalized, and effective ad design. Deploy the updated ad campaign.

[0034] A continuous feedback loop is a fundamental feature of campaign management engine operations, enabling iterative improvements. By collecting performance data (such as clicks and conversion rates of deployed ads), campaign management engines can identify opportunities for optimization, refine the design accordingly, and redeploy updated content to maximize engagement and conversion rates.

[0035] In this approach, the workflow involves defining user preferences through clustering and analysis, generating design requirements, refining ad content using generative models, deploying customized ads, and iterating based on performance metrics. The campaign management engine is built to be scalable, accommodating large datasets and diverse user groups in production environments. It automates traditionally manual processes, adapts to new design features and evolving user preferences, and seamlessly integrates with e-commerce platforms and ad networks to leverage real-time performance data. With its ability to deliver highly personalized, efficient, and impactful ads, the campaign management engine represents a transformative approach to campaign management that increases user engagement and delivers higher conversion rates.

[0036] For example, an e-commerce platform could be used to promote a new smartwatch. The advertiser (seller) targets three distinct user groups: young adults aged 18 to 30, middle-aged customers aged 35 to 50, and seniors aged 60 and above. Initially, three ad designs were created. Ad A, featuring a stylish, modern design with bold imagery and minimalist text, was designed to appeal to young people. Ad B emphasized the health benefits of the smartwatch, targeting middle-aged users who value fitness tracking. Ad C emphasized simplicity and a large, easy-to-read display, designed specifically for seniors.

[0037] As the campaign progressed, performance data revealed differences in engagement. Ad A achieved high conversion rates among young people, but Ad C performed poorly among older adults, who found the ad layout too complex. Ad B achieved some success, but could have resonated better with the target group if it had been more effectively tailored.

[0038] These ads can be dynamically optimized using an advertising campaign management engine. By using ad optimization models generated based on analytics performance metrics and clustering users based on their preferences for ad elements (e.g., text style, images, and layout), these models can be used in conjunction with a design requirement generator to identify user preferences and fine-tune advertising campaigns. For example, older users prefer brighter backgrounds and simplified text, while middle-aged users respond better to prominently displayed, detailed health-related content.

[0039] Using this data, the campaign management engine generates structured prompts for refinement. For example, the engine outputs a JSON file specifying changes such as "increase text size," "use a light background," or "focus on fitness benefits in the tagline." These specifications are handled by a multimodal generative model. For ad C, the engine updates the layout, highlighting key features and replacing complex visuals with clearer, brighter images. For ad B, the engine adjusts the text style to further emphasize health benefits.

[0040] Deploy the updated ads and repeat the cycle. New performance data shows increased engagement among older users, with Ad C now achieving a higher conversion rate. Similarly, after refinement, Ad B resonates more strongly with middle-aged users. Meanwhile, Ad A remains highly effective, but subtle adjustments ensure it aligns with the evolving preferences of younger users.

[0041] This iterative process not only maximizes the effectiveness of each ad but also significantly reduces human intervention. The campaign management engine automates granular generation and application, ensuring ads remain relevant and impactful throughout the campaign. Advertisers benefit from a simplified, scalable solution, while users receive personalized, engaging content tailored to their preferences.

[0042] Example systems and resources

[0043] You can use examples and references Figures 1A to 1D To describe aspects of this technical solution. Figure 1AThis illustrates a sample workflow associated with providing ad management functionality. For example, imagine an e-commerce platform running an online advertising campaign for advertisers to promote a new smartwatch. For this campaign, advertisers target different user groups based on factors such as age, location, gender, and purchase history. Advertisers create ad designs, each targeting a specific user group. For instance, ad A might feature a stylish, modern design, targeting young adults aged 18 to 30; ad B might highlight the health benefits of the smartwatch and appeal to middle-aged customers aged 35 to 50; and ad C might emphasize the smartwatch's ease of use and large display, targeting seniors aged 60 and over.

[0044] However, despite precise targeting, ad success depends heavily on its design. For example, ad A might work well with young people, generating high conversion rates, while ad C might not appeal to older adults, who might find large display features unappealing or prefer a simpler design. Similarly, ad B might resonate with middle-aged customers but fail to attract a younger audience. Due to these differences in preferences, conversion rates, or the percentage of users who buy a smartwatch after seeing the ad, can vary significantly between different groups. For instance, young people might click on ad A and make a purchase, while older adults might ignore ad C, resulting in a lower conversion rate for that group.

[0045] Despite knowing their target audience, advertisers still face the challenge of fine-tuning their ads during campaigns. Ad designers (often third-party agencies) operate separately from e-commerce platforms. While platforms can collect valuable data on the performance of each ad (e.g., which group clicked on which ad and how many made a purchase), it's difficult to immediately refine ad design in response to that data. For example, if ad C performs poorly among older adults, but is still the most suitable ad for that group based on their characteristics, advertisers cannot easily adjust the ad design to make it more appealing. This separation between campaign management and ad design often means longer time to make necessary changes, and by the time adjustments are made, the overall success of the campaign may have already been affected.

[0046] An advertising campaign management engine can be designed to leverage historical campaign performance data (specifically, conversion metrics) to generate dynamic design fine-tuning requirements for specific user groups. These requirements are then used to automatically refine the ads. The campaign management engine supports an iterative process, during which updated designs are rolled out, performance data is collected, and further optimizations are implemented.

[0047] The campaign management engine operates based on three main components: high-conversion design modeling and mining; design requirement generation; and design fine-tuning model. Each component helps create an end-to-end pipeline for dynamic ad refinement.

[0048] High-conversion design modeling and mining focuses on analyzing and modeling design patterns that influence user engagement and conversion rates. This process involves three key steps: user group definition, preference feature mining, and preference linking. User group definition categorizes users into different groups based on their preferences for ad features. Unlike traditional user segmentation based on purchase behavior, this process targets preferences for ad design elements. Techniques such as clustering and feature importance estimation are used to create actionable user profiles.

[0049] Preference feature mining involves the identification and classification of basic features. These features are selected and validated empirically to ensure they can be edited using modern deep learning models. Features are divided into two main categories: ad image processing factors (e.g., image style: exotic, classic; background: bright, light; resolution: high) and ad layout and content adjustment factors (e.g., content selection: key text only, detailed text; text position / size / style: focused slogans, light text; and localization: language-specific options (e.g., Japanese, German)).

[0050] Preference links include linking user profiles to their corresponding design preferences. The combination of manual tagging and data-driven rule mining ensures personalized advertising adjustments for each user group.

[0051] Design requirements can be generated based on users or user groups associated with an advertising campaign. For example, when identifying users, their profiles and associated design preferences are handled by the design requirements generator. This component translates these preferences into structured cues suitable for fine-tuning the model.

[0052] For example:

[0053] Input: User images and product details. Output: JSON format for a specific user group. Design requirements:

[0054] json [

[0056] {

[0057] User Group: "Young Ladies"

[0058] "Design Style": {

[0059] "image":{

[0060] "Style": "Unique"

[0061] Background: Light color

[0062] },

[0063] "content":{

[0064] "Content Selection": "Key Text Only"

[0065] “Text style”: “Focused slogans”

[0066] Language: English

[0067] }

[0068] }

[0069] },

[0070] {

[0071] "User Group": "Otaku"

[0072] "Design Style": {

[0073] "image":{

[0074] "Style": "Anime Art"

[0075] Background: Anime Scenery

[0076] },

[0077] "content":{

[0078] "Content Selection": "Key Text Only"

[0079] "Text Style": "Light Text"

[0080] Language: Japanese

[0081] }

[0082] }

[0083] } ]

[0085] Design fine-tuning (via design fine-tuning models) is achieved using advanced multimodal generative models. These models refine ad elements such as layout, images, and text based on the generated requirements. Image refinement: Using models such as Sega Diffusion, ad images are adapted to meet style preferences (e.g., exotic, bright). Content layout adjustment: Tools such as PosterLLaVa can generate ad layouts where text and images are precisely arranged.

[0086] For example:

[0087] Input: Ad image and layout preferences

[0088] Output: Layout elements in JSON format for rendering:

[0089] json [

[0091] {“Label”: “Title”, “Box”: [0.2, 0.1, 0.8, 0.2]},

[0092] {“Label”: “Subtitle”, “Box”: [0.3, 0.2, 0.7, 0.3]},

[0093] {“Label”: “Object”, “Box”: [0.1, 0.4, 0.9, 0.8]} ]

[0095] Once the updated ads have been fine-tuned, they are deployed in a customized format and displayed to users. Performance data is continuously collected for further refinement.

[0096] Example:

[0097] For young female users who view product advertisements:

[0098] Preferred images: unique, bright, and minimalist; content: focused slogans and concise text. Refined ads integrate these preferences to maximize user engagement and conversion rates.

[0099] Expected Benefits: The expected benefits of this approach are substantial. First, users will be presented with ads tailored to their style preferences, making the ads feel more personalized and relevant. This level of customization can lead to more meaningful content engagement, as ads will better align with the individual user's tastes and interests. Second, the ability to adjust designs based on real-time performance data will improve conversion rates. By continuously refining ad design in response to how well the ad design performs for different user groups, ads will more effectively encourage behaviors such as purchases or registrations. Third, the ad refinement process will be automated, reducing the need for manual intervention from sellers or third-party agencies. This will streamline campaign management, allowing for faster adjustments and minimizing delays. Finally, the campaign management engine will be scalable, featuring an interface that adapts to new design features and evolving user preferences. This flexibility will ensure the platform can adapt to the increasing demands of production-scale deployments, supporting the continuous evolution of advertising strategies as user behavior and market conditions change.

[0100] like Figure 1A As shown, the process begins with advertising campaign data 102A (e.g., detailed ad design performance data and user feedback). This data serves as the basis for identifying patterns in ad performance and user preferences.

[0101] Offline Mining 104A refers to the offline mining process used to extract actionable insights from advertising campaign data. Two main data streams were analyzed: mining ad design performance data and mining user feedback data. Mining ad design performance data involves correlating performance metrics (e.g., clicks, conversion rates) with ad design features (e.g., layout, text, and style). Mining user feedback data examines explicit feedback (e.g., surveys) and implicit feedback (e.g., engagement metrics) to understand user preferences.

[0102] Key mining elements include: Headlines, Text, Content, and Style 106A: Examples of generated insights: Older users prefer more detailed text, larger fonts, and red elements; younger users prefer minimalist, textless ads; and female users are attracted to ads with pink-themed text. Image Style 108A: Examples of style preferences: Female audiences prefer bright, vibrant images; male audiences (especially younger men) prefer darker, more somber visuals. The mined data is used to train an ad optimization model. This model identifies: Ad layout and content adjustment factors 110A: Factors influencing how text and visual elements should be arranged; Ad image processing factors 112A: Style adjustments to image features.

[0103] refer to Figure 1B , Figure 1B Alternative embodiments for high-conversion design modeling and mining are illustrated. It is necessary to identify typical design patterns or features that can be modeled or edited using recent deep learning models, as well as user preferences for these editable design patterns. This can be achieved through offline data mining, which is divided into three main steps. First, user group definition 110B requires classifying users into distinct groups, where each group represents a clear intent or preference for advertising features. This process is similar to conventional user profiling mining for advertising, although the objectives are slightly different. Conventional user profiling mining focuses on grouping users based on their purchase preferences, while this work focuses on user preferences in advertising material design. This is typically achieved using techniques such as user clustering or feature importance estimation.

[0104] Secondly, the 120B preference feature mining requires identifying ad features, as these features must be editable by the AI ​​model. These features are not based on a data-driven approach, but rather manually categorized using empirical methods, and their importance is then validated online. Since ads primarily consist of images and text descriptions of sales items, preference features are categorized into two main types: ad image processing factors and ad layout and content adjustment factors. In the ad campaign management engine, ad image processing factors include image style (unique or classic images), background specifications (bright or light backgrounds), and image detail (e.g., high resolution). For ad layout and content adjustment factors, these features include content selection (only key text or as much ad text as possible), text position / size / style (focused slogans or light text), and language / country (e.g., Japanese, German, or Italian). The ad campaign management engine supports these preference features and has the ability to extend its functionality by providing an interface for adding new features, allowing for continuous upgrades to meet production requirements.

[0105] Finally, Preference Link 130B links the outputs from the user group definition and preference feature mining steps, allowing user profiles to be matched with preference features upon arrival, thus enabling automated personalized ad adjustments. This linking process combines manual tagging and data-driven rule mining. In this way, preference linking in the campaign management engine is a process that connects user profiles or group characteristics identified through user group definitions with specific design preferences extracted through preference feature mining. This connection enables automated and personalized ad adjustments, ensuring that ads resonate with the preferences of the target audience to improve engagement and conversion rates. This process relies on a combination of data-driven rule mining and manual tagging to maintain both accuracy and flexibility.

[0106] Based on demographic data, behavioral patterns, and inferred preferences, user profiles are created for different groups. For example, young professionals can be categorized as preferring trendy, minimalist designs, while older adults might favor ads with larger fonts and brighter backgrounds. Design preferences can also be categorized by characteristics such as text style, image brightness, and layout structure. Some users might prefer bold fonts and centered text, while others might prefer softer tones and off-center designs.

[0107] Preference links then associate these user profiles or groups with relevant design features. Data-driven rule mining analyzes historical data to identify correlations between user attributes and ad performance metrics. For example, patterns in the data might indicate that middle-aged professionals prefer ads characterized by dark blue headlines and detailed descriptions. When data-driven methods are insufficient, manual tagging can ensure that unique or complex preferences are accurately captured and linked to user profiles.

[0108] In a fitness tracker advertising campaign, the campaign management engine might define three user groups: tech-savvy, time-conscious young professionals aged 25 to 35; health- and fitness-focused middle-aged enthusiasts aged 40 to 55; and seniors aged 65 and older who prioritize ease of use and large displays. The design preferences of these groups might indicate that: young professionals prefer bold images and minimalist text; middle-aged enthusiasts favor ads that balance health information with visual appeal; and seniors prefer simple layouts, large fonts, and high-contrast visuals.

[0109] These groups are linked to specific design features through preference links. For young professionals, ads might feature core product images, simple slogans, and modern color palettes such as black and metallic tones. For middle-aged fitness enthusiasts, ads might use a two-column layout, with detailed health information on one side and product visuals on the other. For older adults, ads might include high-contrast backgrounds, large sans-serif fonts, and simplified single-column layouts.

[0110] This linking process allows the system to automatically adjust ad design based on the identified profile. Fitness tracker ads tailored for seniors might feature large, easy-to-read text (such as "Stay Active, Age Not a Thing"), accompanied by bright backgrounds and straightforward calls to action. In contrast, ads targeting young professionals might emphasize the tagline "Track Your Best Performance" and use bold text to cover minimalist product images.

[0111] By automating this process, preference links ensure real-time personalization of ads, significantly improving their relevance and effectiveness across different user groups. This feature not only increases engagement but also supports higher conversion rates by tailoring ads to the specific needs and preferences of their intended audience.

[0112] Turning Figure 1A It provides conditional text template generators (114A and 116A). By using insights from the ad optimization model, the campaign management engine develops conditional text templates for the following purposes: ad layout and content adjustments, which involve customizing poster layouts such as positioning headlines, subheadings, and objects; and ad image adjustments, which refine the style elements of images to meet user preferences.

[0113] Advertising campaign deployment involves the advertiser (seller, 120A) providing an initial campaign, which includes: advertising text 122A, which consists of headlines, slogans or descriptions; and advertising images (124A), which include visual elements such as product photos or graphics.

[0114] The conditional text template generator 114A can apply layout-specific refinements to adjust the advertising poster layout 130A, thereby aligning text elements to maximize engagement. Similarly, the conditional text template generator 116A can fine-tune the advertising image 132A to ensure visual consistency with the identified preferences.

[0115] In the ad refinement and generation phase, refined text and image components are integrated to generate an updated ad 140A. This process employs two advanced generative models: a multimodal ad layout generation model 134A, which generates a consistent layout by coordinating text and visual placement; and an ad image processing model 136A, which performs stylistic adjustments on the image, such as brightness, color balance, or thematic effects.

[0116] like Figure 1C As shown, the conditional text template generator 116A uses a user profile, including a description 150A and attributes 160A (e.g., demographic information, behavioral data, and aesthetic preferences), to fine-tune the ad image. This adjustment process modifies the ad's visual elements (e.g., color scheme, image style, and spatial composition) to align with the preferences and expectations indicated in the user profile. For example, if the user profile specifies a preference for vibrant, high-contrast images and minimalist design, the conditional text template generator 116A will adjust the ad image to reflect these qualities by enhancing brightness, sharpening key visual elements, and removing unnecessary background clutter.

[0117] Similarly, such as Figure 1D As shown, the conditional text template generator 114A, combined with an advanced generative model, further utilizes the same user profile, including description 150A and attribute 160A, to create updated advertisements. This profile integration allows for a holistic approach to ad refinement, where both text and visual elements dynamically align with user preferences. The conditional text template generator 114A generates structured cues that guide the advanced generative model to effectively synthesize and lay out ad content. For example, if the user profile indicates a preference for concise, centered slogans accompanied by visual cues, the generator ensures that the text placement and font style emphasize clarity and impact, while the generative model refines the overall layout and aesthetic consistency of the ad.

[0118] These iterative adjustments, driven by user-centric data and executed by advanced computing tools, produce highly personalized and visually appealing ads designed to maximize user engagement and conversion rates.

[0119] The final output is optimized ads tailored to the preferences of specific user groups, ensuring higher engagement and conversion rates. For example, refined ads targeting older audiences might feature red headlines, large fonts, detailed descriptions, and bright backgrounds. Conversely, ads targeting younger audiences might emphasize simple designs with minimal text and darker, more stylish images.

[0120] This iterative cycle of ad design optimization, deployment, and feedback ensures that the campaign management engine remains dynamic and responsive to evolving user behavior and preferences. The scalability and adaptability of the campaign management engine allow for seamless integration with large advertising platforms, enabling continuous improvements in campaign performance.

[0121] refer to Figure 2A , Figure 2A The project listing system 100 is shown, which includes an artificial intelligence system 100A, an advertising campaign management engine 110, a mining and modeling engine 112, an advertising optimization model 114, an advertising optimization profile, a design requirement generator 118, advertising design performance data 120, advertising campaigns 130, a design fine-tuning model 140, updated advertising campaigns 150, an advertising campaign management engine client 160A (administrator), an advertising campaign management engine client 160B (seller), an advertising campaign management engine client 160C (buyer), and iterative refinement 170.

[0122] The AI ​​system 100A establishes a dynamic framework for optimizing advertising campaigns by iteratively refining ads to align with user preferences and behaviors. At its core is the campaign management engine 110, which coordinates an integrated pipeline for mining data, optimizing ad design, and generating fine-tuned ads.

[0123] The mining and modeling engine 112 performs the initial steps, extracting actionable insights through three core activities: user group definition, preference mining, and preference linking. User group definition categorizes audiences based on attributes such as demographics, behavioral patterns, and aesthetic preferences. For example, users can be segmented into groups such as young professionals who prefer minimalist layouts or families who enjoy vibrant and colorful designs. Preference mining identifies design features that resonate with these groups, such as font size, color palette, and image style. For example, older users might prefer large, clear fonts with detailed text, while younger audiences prefer stylish, text-free designs. Preference linking combines these mined insights with user profiles to build personalized advertising design strategies, such as associating tech-savvy users with bold, high-contrast visuals that emphasize innovation.

[0124] Insights derived from the mining and modeling process inform ad optimization model 114, which generates ad optimization profiles 116 tailored to user groups or individuals. Ad optimization profiles 116 are functionally linked to user descriptions and user attributes used to generate blueprints that specify design tweaks needed to improve engagement and conversion rates. For example, ad optimization profiles may include conditional text templates specifying that environmentally conscious users might emphasize understated color palettes, images reflecting sustainability, and concise text promoting environmental benefits.

[0125] The design requirements generator 118 converts these ad optimization profiles 116 into structured specifications for ad components. These specifications may include instructions for adjusting font sizes, repositioning text elements, or changing the visual tone of images. For example, a minimalist campaign might specify a clean layout that emphasizes product images, minimal text, and ample white space. These specifications are derived from a combination of historical ad design performance data 120 and real-time campaign analysis to ensure relevance and accuracy.

[0126] Campaign 130 corresponds to an advertising campaign provided by the advertiser. Campaign 130 includes original text and visual elements, which serve as the basis for refinement. A design fine-tuning model 140 implements design requirements to generate an improved advertisement. Using an advanced generative model, the fine-tuning process may involve improving font clarity, adjusting image brightness, or repositioning layout elements to maximize visibility and user engagement. The refined output produces an updated campaign 150, which will be deployed to the target audience. This updated campaign 150 follows optimized profiles and design specifications to meet specific user preferences. For example, a campaign designed for older adults might include larger text and a bright background, while a campaign for younger adults emphasizes clean images with a simple, modern text layout.

[0127] Iterative refinement 170 supports a feedback-driven process that continuously improves ad design. Once an updated campaign is deployed, performance metrics such as click-through rate, conversion rate, and engagement duration are collected and analyzed. These metrics inform the mining and modeling engine, enabling refinement for subsequent iterations. For example, if an ad performs poorly due to overly complex visuals, the campaign management engine 110 simplifies the design in the next iteration while retaining the core message elements.

[0128] The campaign management engine 110 operates in conjunction with campaign management engine clients such as administrators (campaign management client 160A), who monitor system operations and metrics; sellers (campaign management client 160B), who provide initial ad content and track campaign success; and buyers (campaign management client 160C), whose interactions and feedback provide performance data for further refinement. These stakeholders collaborate within the ecosystem to achieve optimized advertising results.

[0129] The integration of advanced AI, machine learning, and iterative tuning ensures that each advertising campaign is progressively optimized for higher engagement and conversion rates. The Campaign Management Engine 110 provides advertisers with a scalable and adaptable solution that meets diverse user needs while delivering measurable results, ultimately transforming the dynamic advertising landscape.

[0130] For example, the campaign management engine 110 is designed to utilize historical campaign performance data (i.e., ad design performance data 120), specifically conversion metrics, to generate dynamic design refinements for specific user groups. These refinements are used to automatically adjust ads, with the campaign management engine 110 supporting an iterative process that continuously collects performance data, optimizes designs, and deploys updated content to improve user engagement and conversion rates.

[0131] The advertising campaign management engine 110 operates through a series of interconnected components that work together to create a dynamically refined end-to-end pipeline for advertising. The first key component (i.e., the mining and modeling engine 112) focuses on analyzing design patterns that influence user engagement and conversion rates. This process begins by defining user groups based on their preferences for advertising features (rather than traditional demographic segmentation, which typically focuses on purchasing behavior). Advanced techniques such as clustering and feature importance estimation are used to develop actionable user profiles that highlight advertising features that resonate with specific groups.

[0132] The next step in this process is preference feature mining, which involves identifying and categorizing the design elements that have the greatest impact on user engagement. These features are validated and selected based on their ability to be tailored by modern deep learning models. These features are categorized into categories such as ad image processing (e.g., style, background, resolution) and content tailoring (e.g., text style, targeting, and language preferences). The final step in this stage is preference linking, where user profiles are connected to the design features that best match their preferences. This is achieved through a combination of manual tagging and data-driven rule mining, ensuring that ads are tailored to meet the specific needs of each user group.

[0133] The second major component of the campaign management engine 110 is design requirement generation (e.g., design requirement generator 118), which processes user profiles and design preferences to create structured design prompts. These prompts specify necessary adjustments to various ad components, including image style, text targeting, and localization, and are used by the campaign management engine 110 to design a fine-tuning model. The generated prompts provide input for the next stage of the process, which focuses on fine-tuning the ad design.

[0134] Advanced generative models (e.g., design fine-tuning model 140) are used for design fine-tuning, adjusting the visual and textual elements of the ad. Multimodal models (e.g., image diffusion models) adjust images to conform to style preferences, while a layout generator precisely arranges text and other elements within the ad to meet design requirements. The result is a refined ad design that aligns with the specific preferences of the target user group. Once the ad design is fine-tuned, it is deployed, and performance data (including user interactions and conversion rates) is collected to guide further optimization.

[0135] A continuous feedback loop (i.e., iterative refinement 170) ensures that ads are continuously improved based on real-time performance metrics. Ads can be updated and redeployed periodically to maximize engagement, with each iteration more effectively achieving the desired results. The process of refining ads through this engine allows for extensive customization, ensuring that ads are more relevant and personalized to users, which in turn improves engagement and conversion rates.

[0136] For clarity and effectiveness, a glossary of key terms and concepts related to the technical solution is provided below.

[0137] The Campaign Management Engine 110 also offers scalability, enabling it to adapt to large datasets and evolving user preferences. Automation of the design refinement process reduces the need for manual intervention, streamlining campaign management workflows and allowing for faster, more responsive adjustments. Furthermore, the Campaign Management Engine 110 is adaptable, supporting emerging design features and user preferences to ensure its effectiveness in changing market conditions. This scalability and flexibility make the Campaign Management Engine ideal for production-scale deployments, where rapid iteration and continuous optimization are crucial for successful advertising strategies.

[0138] Ad design performance data (120) refers to historical data collected from advertising campaigns, including performance metrics such as click-through rates and conversion rates, as well as user feedback obtained through explicit surveys or implicit engagement. This data forms the basis for modeling the relationships between user groups, preference traits, and linking mechanisms, which is crucial for optimizing ad design and targeting.

[0139] User group definition is the process of categorizing users into different groups based on attributes such as demographics, behavioral patterns, and inferred preferences. This categorization identifies meaningful groups that share common characteristics, such as a preference for minimalist design or detailed text.

[0140] Preference features (or factors) are editable design characteristics of advertisements, categorized into image processing factors and layout and content adjustment factors. Image processing factors include attributes such as style, brightness, and resolution, while content adjustment factors encompass text positioning, font size, and language localization. These features form the basis for generating conditional text templates and are an integral part of fine-tuning ad design to match user preferences.

[0141] Preference linking is a hybrid framework that connects user profiles with preference features. This process combines data-driven rule mining or machine learning techniques to ensure accurate and personalized ad adjustments for each user or group.

[0142] The Ad Optimization Model 114 is a predictive framework created using insights derived from ad design performance data. It maps relationships between user groups, their preferences, and how these preferences link to specific design elements. The Ad Optimization Model 114 generates conditional text templates and optimization profiles, allowing for the customization of ad layout, content, and image factors to effectively adapt to targeted advertising campaigns.

[0143] An ad optimization profile (e.g., ad optimization profile 116) represents a set of structured data that can be used to specify the finer details required for ad design, including layout adjustments, content tweaks, and image processing, to meet the needs and expectations of the target audience. Ad optimization profiles are associated with user descriptions and user attributes for specific users or user groups.

[0144] Conditional text templates are structured representations of design requirements generated by ad optimization models. These templates specify layout and content adjustment factors, as well as image processing factors, thus providing clear direction for refining ad layouts and visuals to better align with user preferences.

[0145] The design requires Generator 118 (typically implemented as a Large Language Model (LLM)) to create tuning cues based on ad optimization profiles and campaign specifications. By employing a multimodal layout tuning template, the generator produces structured cues specifically tailored for use with the design tuning model.

[0146] Design tweaking model 140 is a generative AI model or multimodal layout generator that adjusts ad layout and visuals based on tweaking cues. These models refine ad elements to create a visually appealing and consistent design that aligns with the preferences of the target audience. Multimodal layout generators are specifically designed to automatically create designs by combining and organizing different types of content (e.g., text and images) into a coherent layout. It typically uses algorithms or AI models to understand and arrange these elements based on context and predefined design principles, thereby enhancing visual appeal and usability.

[0147] A multimodal layout generator can be associated with a multimodal layout fine-tuning cue template, which is a structured input designed to guide fine-tuning of a model to generate or optimize a layout that integrates various types of content (e.g., text and images). It typically includes instructions on how to consider various factors (i.e., ad image processing factors and ad layout and content adjustment factors) to organize and position the different modalities. The LLM can take a multimodal layout fine-tuning cue template associated with an ad optimization profile to generate fine-tuning cues for designing the fine-tuned model.

[0148] The campaign management engine 110 integrates an ad optimization model 114, a design requirement generator 118, and a design fine-tuning model 140. The campaign management engine 110 manages real-time performance metrics, design optimization, and automatic adjustments to support iterative refinement cycles, thereby ensuring continuous improvement of ad campaigns.

[0149] Accessing historical ad design performance data 120 involves retrieving and analyzing metrics and feedback from previous campaigns to identify patterns, user preferences, and factors driving success. This historical ad design performance data 120 is used to generate an ad optimization model that maps relationships between user groups, preferences, and linking mechanisms, thereby producing conditional text templates to guide layout and image adjustments.

[0150] Advertisers provide raw campaign materials (e.g., text and images), which are then processed through an optimization pipeline. The campaign management engine 110 generates ad optimization profiles, which can be used to link user attributes to specific refinement requirements, such as preferred font sizes or image brightness. These ad optimization profiles can be used to generate conditional text templates that inform a design requirement generator, which then transforms these templates into structured fine-tuning prompts.

[0151] The design fine-tuning model 140 uses these tips to adjust ad elements, refining text placement, color schemes, and visuals. The result is a customized ad campaign designed to resonate with specific user preferences. Once deployed, these refined campaigns integrate user preferences into the design, maximizing engagement.

[0152] Performance metrics from deployed ads are fed back into the ad optimization model, enabling the generation of subsequent optimization profiles and updated ads. This iterative refinement and feedback loop ensures that each iteration improves engagement and conversion rates, thereby continuously enhancing the effectiveness of the advertising campaign.

[0153] refer to Figure 2B , Figure 2B A schematic diagram 200B is shown in association with an advertising campaign management engine according to embodiments described herein. The technical solution of the advertising campaign management engine can be illustrated through steps and example advertising campaigns.

[0154] Step 201B: Collect Historical Ad Data – This process begins by collecting historical data from previous ad campaigns to understand performance trends. This includes images used in the campaigns, such as stylish photos of tech products with minimalist designs, and text layout (e.g., bold fonts centered around calls to action like “Buy Now!”). Metrics such as click-through rate (CTR) and conversion percentage are also captured; for example, a particular ad might have a 15% CTR and an 8% conversion rate. For instance, an ad targeting “young professionals” might achieve a 20% CTR by utilizing a simple, minimalist design (representing a preference for minimalism in that segment).

[0155] Step 202B: User Group Definition – Next, users are segmented into different clusters based on demographic and behavioral data. These clusters might include groups such as “tech enthusiasts,” “environmentally conscious shoppers,” and “luxury seekers.” Each cluster reflects unique preferences. For example, “environmentally conscious shoppers” tend to prefer visuals with green hues and messages that emphasize sustainability, such as “eco-friendly. Planet first.” This segmentation ensures that advertising can be tailored to resonate with the specific preferences of each group.

[0156] Step 203B: Preference Feature Mining and Preference Linking—Once user segments are defined, key features of successful ads are extracted and analyzed to determine their impact on performance. This includes visual elements (e.g., whether the image is minimalist, monochrome, or vibrant) and text components (e.g., font size, content length, and layout). For example, "tech enthusiasts" show higher engagement rates for ads characterized by bold, center-aligned fonts and minimalist product images. Identifying these preferences allows the system to fine-tune ad elements to better meet user expectations.

[0157] Step 204B: Ad Design Optimization Model Training – The ad campaign management engine then trains an AI model to link user preferences with high-performance ad features. Convolutional Neural Networks (CNNs) can be used to analyze image preferences, while the converter handles text optimization. For example, the model might predict that an ad targeting “luxury seekers” would achieve a 25% CTR if it included high-resolution images of luxury goods, gold-themed fonts, and a clean, minimalist layout. These predictions guide ad design to maximize engagement.

[0158] Step 205B: Design Fine-tuning – After the ad design optimization model is in place, the campaign management engine can update ads based on the ad optimization profile, the ad optimization model, and the design fine-tuning model. It is conceivable that in some embodiments, ads can be dynamically updated in real time as users interact with the platform. For example, a user identified as a “tech enthusiast” might see a stylish black-and-white ad with bold text emphasizing innovation. Meanwhile, an “environmentally conscious shopper” might encounter ads with green tones and messages about sustainability. This real-time adjustment ensures that content immediately resonates with viewers, thereby increasing the likelihood of interaction.

[0159] Step 206B: User Engagement and Feedback – After deploying optimized and / or personalized ads, the campaign management engine tracks user engagement, including metrics such as CTR, conversion rate, and the amount of time spent interacting with the ads. For example, a newly designed ad targeting “young professionals” might achieve a 30% CTR, indicating a successful adjustment. This feedback loop provides valuable data for evaluating the effectiveness of different ad elements.

[0160] Step 207B: Iterative Optimization Using Performance Data – Finally, the campaign management engine periodically updates its AI model with the latest data to ensure continued accuracy and relevance. For example, new data might reveal that “tech enthusiasts” have developed a preference for dark mode themed ads, prompting the system to adjust its recommendations. By retraining the model using new insights, the campaign management engine stays adapted to evolving user preferences and market trends.

[0161] For example, historical data analysis reveals that younger users are more likely to engage with minimalist ad designs characterized by bold imagery. This insight guides the creation of conditional text templates that prioritize minimizing text and enhancing the prominence of visual elements in future campaigns. By aligning with these preferences, the campaign management engine ensures that ad designs effectively resonate with this demographic.

[0162] The ad optimization profile creation process links specific user groups with their unique preferences. For example, middle-aged professionals are identified as preferring detailed text and soft color schemes. Ad optimization profiles are generated for this user group, which can be used for design adjustments, such as dark blue centered headlines and supporting text positioned below, to ensure clarity and meet their expectations.

[0163] By using these ad optimization profiles, the design requirements generator creates structured cues to guide the refinement process. In an environmental awareness campaign, the design requirements generator produces fine-tuning cues that instruct the design refinement model to incorporate natural elements into the images and apply green hues to the text layout. These cues ensure that the resulting ads effectively communicate with the intended audience.

[0164] The fine-tuning process itself utilizes advanced generative models to refine ad elements. For example, an ad for a smartwatch adjusts its image by increasing brightness and applying contrast enhancement to highlight key product features. Simultaneously, the accompanying text is repositioned to the top right corner to improve readability and draw attention to crucial details.

[0165] When deployed campaigns underperform, the campaign management engine iterates and improves. In a scenario targeting older users, ads with overly complex visuals and small fonts were redesigned. The layout was simplified, font size increased, and the background was changed to a lighter tone. These adjustments led to increased engagement, demonstrating the system's ability to dynamically adapt to feedback. By combining advanced analytics, machine learning, and generative design tools, this approach automates ad refinement, ensuring ads remain scalable, adaptable, and customizable to user needs. Each iteration delivers more personalized and effective campaigns, increasing engagement and achieving measurable results.

[0166] Examples and references are available. Figures 1A to 1D , Figure 2A and Figure 2B To describe aspects of this technical solution. Figure 2A Based on reference Figure 6 , Figure 7 and Figure 8 The above is an exemplary technical solution environment block diagram for implementing example environments of technical solution embodiments. Typically, the technical solution environment includes a technical solution system suitable for providing an example item list system 100 that can employ the methods of this disclosure. Specifically, Figure 2A A high-level architecture of an item list system 600 according to an embodiment of this disclosure is shown. In addition to other engines, managers, generators, selectors, or components not shown (collectively referred to herein as "components"), Figure 2A The project list system supports 100% Figures 1A to 1D The functions described above.

[0167] Example Method

[0168] refer to Figure 3 , Figure 4 and Figure 5 The flowchart illustrates a method for providing an advertising campaign management engine within an artificial intelligence system. This method can be executed using the artificial intelligence system described herein. In embodiments, one or more computer storage media include computer-executable or computer-usable instructions that, when executed by one or more processors, cause the one or more processors to perform methods (e.g., computer-implemented methods) within the artificial intelligence system (e.g., a computerized system or computer system).

[0169] Turning Figure 3 A flowchart is provided illustrating method 300 for providing an advertising campaign management engine in an artificial intelligence system. At box 302, historical ad design performance data associated with multiple historical ad campaigns is accessed. At box 304, an ad optimization model is generated. At box 306, the ad campaign is accessed. At box 308, an ad optimization profile for the ad campaign is generated. At box 310, fine-tuning tips are generated based on the ad optimization profile for the ad campaign. At box 312, an updated ad campaign is generated. At box 314, the updated ad campaign is deployed.

[0170] Turning Figure 4 A flowchart is provided illustrating method 400 for providing an advertising campaign management engine in an artificial intelligence system. At box 402, the advertising campaign is accessed. At box 404, an ad optimization profile for the advertising campaign is generated, which is associated with a user. At box 406, a fine-tuning cue is generated based on the ad optimization profile and the advertising campaign. At box 408, the updated campaign is generated. At box 410, the updated campaign is deployed to be presented to the user associated with the ad optimization profile.

[0171] Turning Figure 5 The document provides a flowchart illustrating method 500 for providing an advertising campaign management engine within an artificial intelligence system. In box 502, historical ad design performance data associated with multiple historical ad campaigns is accessed. This historical ad design performance data includes ad performance metrics and user feedback data. In box 504, an ad optimization model is generated. This model is generated based on offline operations, which include data analysis of user segmentation and preference insights associated with the ad design performance data. In box 506, the ad optimization model is deployed.

[0172] Technological improvements

[0173] Embodiments of the invention have been described with reference to several inventive features (e.g., operations, systems, engines, and components) associated with an item listing system. The described inventive features include the operations, interfaces, data structures, and arrangements of computing resources associated with providing the functionality described herein with respect to an advertising campaign management engine associated with an artificial intelligence system.

[0174] Embodiments of this invention relate to the field of computing, and more specifically, to artificial intelligence systems. The exemplary embodiments described below specifically provide a system, method, and program product for performing generative AI security engine operations that provide advertising campaign management. Therefore, embodiments of this application improve the technical field of artificial intelligence technology and item list platform technology, enhancing the efficiency and effectiveness of advertising management through advanced data-driven technologies and automation. For example, by leveraging AI to analyze historical ad design performance data, user preferences, and feedback, embodiments can dynamically and precisely optimize ads tailored to specific user groups or individuals. Integrating AI into the advertising campaign management process reduces computational redundancy through automated iterative adjustments, thereby eliminating the need for repetitive manual refinement. Furthermore, the use of advanced generative models and structured prompts ensures that ad layout and design conform to user preferences in real time, significantly improving engagement rates and conversion results.

[0175] On the item listing platform, these implementations enhance the relevance of ads displayed to users, resulting in a better overall user experience. This personalization increases the likelihood of conversions, directly benefiting advertisers, while optimizing platform resource usage by prioritizing high-performance ad placements. The combination of scalability, adaptability, and real-time optimization makes these implementations a significant advancement in artificial intelligence and item listing platform technology.

[0176] The functionality of embodiments of the invention has been further described through implementations and anecdotal examples—demonstrating that the operation of using an advertising campaign management engine in an artificial intelligence system to provide advertising campaign management serves as a solution to a specific problem in artificial intelligence technology, thereby improving computational operations in the artificial intelligence system. Overall, these improvements result in less CPU computation, lower memory requirements, and increased flexibility in the artificial intelligence system compared to conventional artificial intelligence system operations performed for similar functionality.

[0177] Additional support for the detailed description of the invention

[0178] Example project list system environment

[0179] Now for reference Figure 6 , Figure 6 A computing environment for an example item listing system 600 capable of employing embodiments of this disclosure is shown. Specifically, Figure 6 A high-level architecture of platform 610, which is a sample project list platform that can host a technology solution environment or a part thereof, is shown. It should be understood that this arrangement and other arrangements described herein are illustrated as examples. For example, as mentioned above, many of the elements described herein can be implemented as discrete or distributed components or combined with other components, and implemented in any suitable combination and location. Other arrangements and elements (e.g., machine, interface, function, command, and function groupings) may be used in addition to or in place of the arrangements and elements shown.

[0180] The project listing system 600 may be a cloud computing environment that provides computing resources for the functions associated with the project listing platform 610. For example, the project listing system 600 supports the delivery of computing components and services, including servers, storage, databases, networks, applications, and machine learning associated with the project listing platform 610 and client devices 620. Multiple client devices (e.g., client device 620) include hardware or software for accessing resources on the project listing system 600. Client device 620 may include applications (e.g., client application 622) and interface data (e.g., client application interface data 624) that support client functions associated with the project listing system. Multiple client devices may access the computing components of the project listing system 600 via a network (e.g., network 630) to perform computing operations.

[0181] The project listing platform 610 is responsible for providing the computing environment or architecture that supports the infrastructure for providing project listing platform functionality (e.g., e-commerce functionality). The project listing platform supports storing projects in a project database and provides a search system for receiving queries and identifying search results based on those queries. The project listing platform can also provide a computing environment with features for managing, selling, purchasing, and recommending different types of projects. The project listing platform 610 can be specifically used as a content platform, such as the eBay content platform or e-commerce platform developed by eBay Inc. of San Jose, California.

[0182] The project list platform 610 can provide project list operations 630 and project list interfaces 640. Project list operations 630 may include service operations, communication operations, resource management operations, security operations, and fault-tolerant operations that support specific tasks or functions within the project list platform 610. Project list interfaces 640 may include service interfaces, communication interfaces, resource interfaces, security interfaces, and management and monitoring interfaces that support functions between project list platform components. Project list operations 630 and project list interfaces 640 enable communication, coordination, and seamless operation of the project list system 600.

[0183] As an example, the functionalities associated with the item listing platform 610 may include shopping operations (e.g., product search and browsing, product selection and shopping cart, checkout and payment, and order tracking); user account operations (e.g., user registration and authentication, and user profiles); seller and product management operations (e.g., seller registration and product listing, and inventory management); payment and financial operations (e.g., payment processing, refunds, and returns); order fulfillment operations (e.g., order processing and fulfillment, and inventory management); customer support and communication interfaces (e.g., customer support chat / email and notifications); security and privacy interfaces (e.g., authentication and authorization, payment security); recommendation and personalization interfaces (e.g., product recommendations and customer reviews and ratings); analytics and reporting interfaces (e.g., sales and inventory reports, and user behavior analytics); and APIs and integration interfaces (e.g., APIs for third-party integration).

[0184] The project listing platform 610 can provide a project listing platform database (e.g., project listing platform database 650) to effectively manage and store different types of data. The project listing platform database 650 may include relational databases, NoSQL databases, search databases, cache databases, content management systems, analytics databases, payment gateway databases, customer relationship management databases, log and error databases, inventory and supply chain databases, and multi-channel databases used in combination to effectively manage data and provide users with an e-commerce experience.

[0185] The project listing platform 610 supports applications (e.g., application 660), which are computer programs, software components, or services that serve specific functions or sets of functions to meet the requirements of a specific project listing platform or user requirements. Applications can be client-side (user-facing) and server-side (backend). Applications can also include applications without any AI support (e.g., application 662), applications supported by traditional AI models (e.g., application 664), and applications supported by generative AI models (e.g., application 666). As examples, applications may include online storefront applications, mobile shopping applications, application and management consoles, payment gateway integrations, user account and authentication applications, search and recommendation engines, inventory and stock management applications, order processing and fulfillment applications, customer support and communication tools, content management systems, analytics and reporting applications, marketing and promotion applications, multi-channel integration applications, log and bug tracking applications, customer relationship management (CRM) applications, security applications, and APIs and web services used in combination to effectively provide users with an e-commerce experience.

[0186] Platform 610 in the project list may include a machine learning engine (e.g., machine learning engine 670). Machine learning engine 670 refers to a machine learning framework or platform that provides the infrastructure and tools for designing, training, evaluating, and deploying machine learning models. Machine learning engine 670 can serve as the backbone for developing and deploying machine learning applications and solutions. Machine learning engine 670 may also provide tools for visualizing data and model results, as well as interpreting model decisions to understand how the model makes predictions.

[0187] The Machine Learning Engine 670 provides the necessary libraries, algorithms, and utilities to perform various tasks within a machine learning workflow. Machine learning workflows can include data processing, model selection, model training, model evaluation, hyperparameter tuning, scalability, model deployment, inference, integration, customization, and data visualization. The Machine Learning Engine 670 can include pre-trained models for various tasks, thus simplifying the development process. In this way, the Machine Learning Engine 670 streamlines the entire machine learning process, from data preparation and model training to deployment and inference, making it accessible and efficient for different types of users engaged in a wide range of machine learning applications—e.g., clients, data scientists, machine learning engineers, and developers.

[0188] Machine learning engine 670 can be implemented as a component in item list system 600, which leverages machine learning algorithms and techniques (e.g., machine learning algorithm 672) to enhance various aspects of the item list system's functionality. Machine learning engine 670 can provide a range of machine learning algorithms and techniques for teaching computers to learn from data and make predictions or decisions without explicit programming. These techniques are widely used in various applications across different industries and can include examples such as: supervised learning (e.g., linear regression: classification, support vector machines (SVM)); unsupervised learning (e.g., clustering, principal component analysis (PCA), association rules (e.g., priors)); reinforcement learning (e.g., Q-learning, deep Q-networks (DQN)); and deep learning (e.g., neural networks, convolutional neural networks (CNN), and recurrent neural networks (RNN)); and ensemble learning random forests.

[0189] Machine Learning Training Data 120 supports the process of building, training, and fine-tuning machine learning models. Machine Learning Training Data 120 consists of labeled datasets used to teach machine learning models to recognize patterns, make predictions, or perform specific tasks. Training data typically includes two main components: input features (X) and labels or target values ​​(Y). Input features can include variables, attributes, or characteristics that serve as input to the machine learning model. Input features (X) can be numerical, categorical, or even textual, depending on the nature of the problem. For example, in a model used to predict house prices, input features might include the number of bedrooms, square feet, neighborhood, etc. Labels or target values ​​(Y) include the values ​​that the model aims to predict or classify. Labels represent the expected output or basic fact for each corresponding set of input features. For example, in a spam classifier, labels would indicate whether each email is spam (i.e., binary classification). The training process involves presenting training data to the model, and the model learns to make predictions or decisions by recognizing patterns and relationships between the input features (X) and target values ​​(Y). Machine learning algorithms adjust their internal parameters during training to minimize the discrepancy between their predictions and the actual labels in the training data. The Machine Learning Engine 670 can use historical and real-time data to train models and make predictions, thereby continuously improving performance and user experience.

[0190] Machine learning engine 670 may include machine learning models (e.g., machine learning model 676) generated using machine learning engine workflows. Machine learning model 676 may include generative AI models and traditional AI models, both of which can be used in item listing system 600. Generative AI models are designed to generate new data (typically in the form of text, images, or other media) based on patterns and knowledge learned from existing data. Generative AI models can be used in a variety of ways, including: content generation, product image generation, personalized product recommendations, natural language chatbots, and content summarization. Traditional AI models encompass a wide range of algorithms and techniques and can be used in a variety of ways, including: recommender systems, predictive analytics, search algorithms, fraud detection, customer segmentation, image classification, natural language processing (NLP), and A / B testing and optimization. In many cases, a combination of generative AI models and traditional AI models can be used to deliver a comprehensive and efficient e-commerce experience, combining data-driven insights and creativity.

[0191] The Machine Learning Engine 670 can be used to analyze data, make predictions, and automate processes to provide users with a more personalized and efficient shopping experience. Examples include product recommendation search and filtering; pricing optimization; inventory and stock management; customer segmentation; customer churn prediction and retention; fraud detection; sentiment analysis; customer support and chatbots; image and video analytics; and ad targeting and marketing. The specific applications of machine learning within the Project Listing Platform 610 can vary depending on the specific objectives, available data, and resources.

[0192] Example Distributed Computing System Environment

[0193] Now for reference Figure 7 , Figure 7 An example distributed computing environment 700 capable of employing embodiments of the present disclosure is shown. Specifically, Figure 7 A high-level architecture of an example cloud computing platform 710 capable of hosting a technology solution environment or a portion thereof (e.g., a data trustee environment) is illustrated. It should be understood that such and other arrangements described herein are merely illustrative examples. For instance, as stated above, many of the elements described herein can be implemented as discrete or distributed components or in combination with other components, and in any suitable combination and location. Other arrangements and elements (e.g., machines, interfaces, functions, commands, and function groups) may be used in addition to or in place of the arrangements and elements shown.

[0194] The data center can support a distributed computing environment 700, which includes a cloud computing platform 710, racks 720, and nodes 730 (e.g., computing devices, processing units, or blades) within the racks 720. A technology solution environment can be implemented using the cloud computing platform 710, which runs cloud services across different data centers and geographic regions. The cloud computing platform 710 can implement a structure controller 740 component for providing and managing the allocation, deployment, upgrades, and management of cloud services. Typically, the cloud computing platform 710 is used to store data or run service applications in a distributed manner. The cloud computing infrastructure 710 in the data center can be configured to host and support the operation of endpoints for specific service applications. The cloud computing infrastructure 710 can be a public cloud, a private cloud, or a dedicated cloud.

[0195] Node 730 may provide a host 750 (e.g., an operating system or runtime environment) on which a defined software stack runs on Node 730. Node 730 may also be configured to perform specialized functions (e.g., compute nodes or storage nodes) within the cloud computing platform 710. Node 730 is allocated to run one or more portions of a tenant's service application. A tenant may refer to a customer utilizing the resources of the cloud computing platform 710. The service application components of the cloud computing platform 710 that support a particular tenant may be referred to as multi-tenant infrastructure or lease. In this document, the terms service application, application, or service are used interchangeably and broadly refer to any software or software portion that runs on top of or accesses storage and compute equipment locations within the data center.

[0196] When node 730 is supporting multiple individual service applications, node 730 can be partitioned into virtual machines (e.g., virtual machine 752 and virtual machine 754). Physical machines can also run individual service applications simultaneously. Virtual machines or physical machines can be configured as personalized computing environments supported by resources 760 (e.g., hardware and software resources) in the cloud computing platform 710. It is envisioned that resources can be configured for specific service applications. Furthermore, each service application can be divided into functional parts, allowing each functional part to run on a separate virtual machine. In the cloud computing platform 710, multiple servers can be used to run service applications and perform data storage operations within a cluster. Specifically, servers can perform data operations independently but are exposed as a single device referred to as a cluster. Each server in the cluster can be implemented as a node.

[0197] Client device 780 can connect to service applications in cloud computing platform 710. Client device 780 can be configured to correspond to a reference... Figure 7 Any type of computing device in the computing device 700, such as client device 780, can be configured to issue commands to the cloud computing platform 710. In embodiments, client device 780 can communicate with service applications via Virtual Internet Protocol (IP) and load balancers or other means that direct communication requests to a specified endpoint in the cloud computing platform 710. Components of the cloud computing platform 710 can communicate with each other via a network (not shown), which may include, but is not limited to, one or more local area networks (LANs) and / or wide area networks (WANs).

[0198] Example computing environment

[0199] Having briefly described the overview of embodiments of the present invention, the following describes an example operating environment in which embodiments of the present invention can be implemented, in order to provide a general context for various aspects of the present invention. Specifically, reference is made first to... Figure 8An example operating environment for implementing embodiments of the present invention is shown and is generally designated as computing device 800. Computing device 800 is merely an example of a suitable computing environment and is not intended to imply any limitation on the scope or functionality of the invention. Nor should computing device 800 be construed as having any dependency or requirement associated with any one or combination of the illustrated components.

[0200] The invention can be described in the general context of computer code or machine-usable instructions, including computer-executable instructions (e.g., program modules) that are executed by a computer or other machine (e.g., a personal data assistant or other handheld device). Generally, a program module, including routines, programs, objects, components, data structures, etc., refers to code that performs a task or implements a specific abstract data type. The invention can be practiced in a variety of system configurations, including handheld devices, consumer electronics, general-purpose computers, and more specialized computing devices. The invention can also be practiced in distributed computing environments, where tasks are performed by remote processing devices linked via a communication network.

[0201] refer to Figure 8 The computing device 800 includes a bus 810 that directly or indirectly couples to the following devices: memory 812, one or more processors 814, one or more presentation components 816, input / output ports 818, input / output components 820, and a schematic power supply 822. Bus 810 represents one or more buses (e.g., an address bus, a data bus, or a combination thereof). For clarity of concept, Figure 8 The various boxes are shown with lines, and other arrangements of the described components and / or component functions are also envisioned. For example, a presentation component such as a display device can be considered an I / O component. Furthermore, the processor has memory. We recognize this as essential to the art and reiterate... Figure 8 The figures are merely illustrative examples of computing devices that can be used in conjunction with one or more embodiments of the present invention. There is no distinction between categories such as “workstation,” “server,” “laptop,” and “handheld device,” as all of these categories are... Figure 8 Within the scope and with reference to "Computing Devices".

[0202] Computing device 800 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by computing device 800, and includes volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, computer-readable media can include computer storage media and communication media.

[0203] Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to: RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, Digital Universal Optical Disc (DVD) or other optical disc storage devices, magnetic tape cassettes, magnetic tape, disk storage devices or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computing device 800. Computer storage media themselves do not include signals.

[0204] Communication media typically embody computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals (e.g., carrier waves or other transmission mechanisms), and include any information transmission medium. The term "modulated data signal" refers to a signal whose characteristics are set or altered in a manner that encodes information in the signal. By way of example, and not limitation, communication media include wired media such as wired networks or direct wired connections, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination of the above should also be included within the scope of computer-readable media.

[0205] Memory 812 includes computer storage media in the form of volatile and / or non-volatile memory. The memory can be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. Computing device 800 includes one or more processors that read data from various entities such as memory 812 or I / O components 820. Presentation component 816 presents data indications to a user or other device. Exemplary presentation components include display devices, speakers, printing components, vibration components, etc.

[0206] I / O port 818 allows computing device 800 to be logically coupled to other devices, including I / O components 820 (some of which may be built-in). Illustrative components include microphones, joysticks, game controllers, satellite antennas, scanners, printers, wireless devices, etc.

[0207] Additional structural and functional features of embodiments of the technical solution

[0208] Having identified the various components used herein, it should be understood that any number of components and arrangements can be employed to achieve the desired functionality within the scope of this disclosure. For example, for clarity of concept, components in the embodiments depicted in the accompanying drawings are shown in lines. Other arrangements of these and other components can also be implemented. For example, although some components are depicted as single components, many elements described herein can be implemented as discrete or distributed components or combined with other components, and implemented in any suitable combination and location. Some elements may be omitted entirely. Furthermore, as described below, the various functions performed by one or more entities described herein can be performed by hardware, firmware, and / or software. For example, various functions can be performed by a processor executing instructions stored in memory. Therefore, other arrangements and elements (e.g., machines, interfaces, functions, commands, and function groups) may be used in addition to or in place of the arrangements and elements shown.

[0209] The embodiments described in the following paragraphs can be combined with one or more of the specifically described alternatives. Specifically, the claimed embodiments may include references to more than one other embodiment in the alternatives. The claimed embodiments may specify additional limitations on the claimed subject matter.

[0210] This document specifically describes the subject matter of embodiments of the invention to meet legal requirements. However, this specification itself is not intended to limit the scope of this patent. Rather, the inventors have envisioned that the claimed subject matter may also be embodied in other ways in combination with other prior art or future art to include different steps or combinations of steps similar to those described in this document. Furthermore, although the terms “step” and / or “box” may be used herein to denote different elements of the method employed, such terms should not be construed as implying any particular order between or between the various steps disclosed herein, unless and only if the order of the various steps is explicitly described.

[0211] For the purposes of this disclosure, the word "comprising" has the same broad meaning as the word "including," and the word "access" includes "receiving," "quoting," or "retrieval." Furthermore, the word "communication" has the same broad meaning as the words "receiving" or "transmitting," which is facilitated by a software- or hardware-based bus, receiver, or transmitter using the communication medium described herein. Additionally, unless otherwise stated, words such as "a" or "an" include both plural and singular forms. Thus, for example, the constraint "one feature" is satisfied when one or more features are present. Furthermore, the term "or" includes conjunctions, disjunctives, and both (a or b therefore includes a or b, and a and b).

[0212] For the purposes of the detailed discussion above, embodiments of the present invention are described with reference to a distributed computing environment; however, the distributed computing environment described herein is merely exemplary. Components may be configured to perform novel aspects of the embodiments, wherein the term "configured for" may mean "programmed to" perform a specific task or implement a specific abstract data type using code. Furthermore, while embodiments of the present invention can generally be referred to in the technical environment and illustrations described herein, it should be understood that the described techniques can be extended to other implementation contexts.

[0213] Embodiments of the invention have been described with respect to specific embodiments intended to be illustrative and not limiting in all respects. Alternative embodiments will become apparent to those skilled in the art without departing from the scope of the invention.

[0214] As can be seen from the foregoing, this invention is well-suited to achieving all the goals and objectives set forth herein, as well as other obvious and inherent advantages of the structure.

[0215] It should be understood that certain features and sub-combinations are useful and can be employed without reference to other features or sub-combinations. This is contemplated by the claims and is within the scope of the claims.

Claims

1. A computerized system, comprising: One or more computer processors; as well as A computer memory that stores computer-usable instructions, which, when used by the one or more computer processors, cause the one or more computer processors to perform operations, the operations including: Access historical ad design performance data associated with multiple historical ad campaigns; Based on the historical ad design performance data, an ad optimization model is generated, wherein the ad optimization model is generated based on the modeling relationship between user groups, preference features, and preference links; Access advertising campaigns; Using the advertising optimization model and the advertising campaign, generate the advertising optimization configuration file for the advertising campaign; Use the design requirements generator to generate fine-tuning tips based on the ad optimization profile and the ad campaign; Generate updated advertising campaigns using design fine-tuning models and fine-tuning tips; and Deploy the updated advertising campaign.

2. The system according to claim 1, wherein, The historical ad design performance data includes ad performance metrics and user feedback data. The ad optimization model is generated based on offline operations, which include data analysis of user segmentation and preference insights associated with the historical ad design performance data.

3. The system according to claim 1, wherein, The preference features include factors related to ad image processing, as well as factors related to ad layout and content adjustment.

4. The system according to claim 1, wherein, The preference linking is based on a hybrid linking framework that is associated with manual tagging and data-driven rule mining or machine learning.

5. The system according to claim 1, wherein, The advertising optimization model operates to generate conditional text templates associated with: advertising layout and content adjustment factors or advertising image processing factors associated with the advertising optimization profile corresponding to the advertising campaign.

6. The system according to claim 1, wherein, The design requirement generator is a large language model that uses a multimodal layout fine-tuning cue template associated with an ad optimization profile to generate fine-tuning cue for designing a fine-tuning model. The multimodal layout fine-tuning cue template is a structured data format that defines key predefined elements for generating fine-tuning cue.

7. The system according to claim 1, wherein, The design fine-tuning model is a multimodal layout generator that adjusts the advertising campaign based on the fine-tuning prompts.

8. The system according to claim 1, wherein, The generation of the updated advertising campaign is also based on user preferences used to update the advertising campaign.

9. The system according to claim 1, wherein the operation further comprises: Access the updated ad design performance data for the advertising campaign; Using the updated ad design performance data of the ad campaign, the ad optimization model, and the updated ad campaign, generate a subsequent ad optimization configuration file for the updated ad campaign; Using the design requirement generator, generate subsequent fine-tuning prompts based on the subsequent ad optimization profile and the updated ad campaign; Using the design fine-tuning model and the subsequent fine-tuning tips, generate subsequent updated advertising campaigns; as well as Deploy the subsequently updated advertising campaign.

10. The system according to claim 1, wherein, The ad optimization model, the design requirement generator, and the design fine-tuning model define an ad campaign management engine associated with real-time performance metrics, design optimization, and automatic adjustments.

11. One or more computer storage media having computer-executable instructions embodied thereon, the computer-executable instructions, when executed by a computing system having a processor and a memory, causing the processor to perform operations, the operations including: Access advertising campaigns; Using the advertising optimization model and the advertising campaign, an advertising optimization profile for the advertising campaign is generated, wherein the advertising optimization profile is associated with the user; Use the design requirements generator to generate fine-tuning tips based on the ad optimization profile and the ad campaign; Generate updated advertising campaigns using design fine-tuning models and fine-tuning tips; and Deploy the updated advertising campaign to present it to users associated with the advertising optimization profile.

12. The medium according to claim 11, wherein, The ad design performance data includes ad performance metrics and user feedback data. The ad optimization model is generated based on offline operations, which include data analysis of user segmentation and preference insights associated with the ad design performance data.

13. The medium according to claim 11, wherein, The ad optimization configuration file is associated with the user's profile and attributes, which are used to adjust ad layout and content adjustment factors, as well as ad image processing factors, to generate the updated ad campaign.

14. The medium according to claim 11, wherein, Preference characteristics include factors related to ad image processing, as well as factors related to ad layout and content adjustments.

15. The medium according to claim 11, wherein, The advertising optimization model operates to generate conditional text templates associated with: advertising layout and content adjustment factors or advertising image processing factors associated with the advertising optimization profile corresponding to the advertising campaign.

16. A computer-implemented method, the method comprising: Access advertising campaigns; Using the advertising optimization model and the advertising campaign, generate the advertising optimization configuration file for the advertising campaign; Use the design requirements generator to generate fine-tuning tips based on the ad optimization profile and the ad campaign; Using the design fine-tuning model and the fine-tuning tips, an updated advertising campaign is generated; as well as Deploy the updated advertising campaign.

17. The method according to claim 16, wherein, The ad design performance data includes ad performance metrics and user feedback data, wherein the ad optimization model is generated based on offline operations, which include data analysis of user segmentation and preference insights associated with the ad design performance data.

18. The method according to claim 16, wherein, The ad optimization profile is associated with a user profile of a user or target user group, which is used to adjust ad layout and content adjustment factors, as well as ad image processing factors, to generate the updated ad campaign.

19. The method of claim 16, wherein, Preference characteristics include factors related to ad image processing, as well as factors related to ad layout and content adjustments.

20. The method of claim 16, wherein, The advertising optimization model operates to generate conditional text templates associated with: advertising layout and content adjustment factors or advertising image processing factors associated with the advertising optimization profile corresponding to the advertising campaign.

Images