Dynamic Banner Ad Design and Adjustment System Based on User Behavior Analysis

Abstract

A dynamic banner ad design and adjustment system based on user behavior analysis is disclosed. The interactive behavior analysis module is connected to the banner ad database and the user database. The personalized banner ad generation module is connected to the interactive behavior analysis module, and the behavior feedback module is connected to the personalized banner ad generation module. Through the collaborative operation of the above modules, the system integrates the user's historical interactive behavior, preference characteristics, and design element information of different versions of banner ads. This enables the system to automatically compare the ad content with the user's behavioral characteristics and generate personalized banner ads that meet the user's needs through dynamic content selection and design configuration. This provides an ad presentation mechanism that can be continuously adjusted and cyclically optimized.

Description

Dynamic Banner Ad Design and Adjustment System Based on User Behavior Analysis Technical Field

[0001] This invention relates to a dynamic banner ad design and adjustment system, which utilizes user browsing behavior information, interaction behavior characteristics, and historical behavior performance on websites or platforms as the basis for dynamically generating personalized banner ads. It calculates interaction behavior indicators through a behavior analysis model to automatically adjust the ad content selection strategy and ad design rules, thereby improving the matching degree between banner ads and user preferences, increasing click-through rate and conversion rate, and enhancing the consistency and accuracy of the website browsing experience. This is a user behavior analysis-based dynamic banner ad design and adjustment system. Prior Technology

[0002] In current website advertising technologies and digital marketing systems, most banner ad delivery logic is still primarily statically configured, typically selecting ad content based on the type of page viewed, basic customer attributes, or pre-set marketing rules. While such systems can provide ad creatives for different pages to some extent, they cannot adjust in real time based on actual user interactions. For example, traditional banner ad systems usually display a single version of the ad design using a fixed template, lacking the ability to provide different ad versions for different users, and also struggling to dynamically adjust ad presentation based on differences in user preferences, usage time, or operating devices. Therefore, existing technologies can only provide a basic browsing experience and cannot achieve the behavior-oriented personalized mechanism required for precise ad delivery.

[0003] Furthermore, existing advertising management and analysis systems often focus on overall data statistics, such as relatively crude advertising performance metrics like impressions, clicks, and click-through rates, failing to delve deeper into the detailed user interactions with ads. Behavioral data that better reflects the actual effectiveness of ads, such as mouse hover time, scrolling time, interaction depth, number of times users enter the application process, and final conversion rate, are typically not integrated into the ad placement decision model. In addition, traditional technologies cannot analyze in detail the impact of different ad design elements (such as font size, layout, image style, CTA button format, and color scheme) on the interaction effectiveness of different user groups or in different contexts. Therefore, in existing technologies, even if multiple design versions of the same ad content exist, the impact of their design differences on user responses cannot be effectively quantified and quantified, making it impossible to establish a systematic ad design optimization mechanism.

[0004] Furthermore, traditional advertising presentation methods typically lack real-time feedback and automated learning capabilities, making it impossible to adjust subsequent ad content or design rules based on users' latest behavioral responses. For example, when users exhibit significantly better interaction performance in certain ad versions, existing systems often continue to display ad creatives with a fixed proportion or schedule, failing to automatically increase the exposure ratio of high-performing versions. Conversely, when certain ad versions consistently underperform, it is difficult to automatically reduce their weight or adjust their presentation conditions. In addition, existing systems cannot incorporate individual user interaction performance into subsequent ad content selection strategies, preventing ad presentation patterns from continuously evolving based on user preferences and maintaining only a static and fixed logic. This lack of dynamic adjustment capabilities prevents advertising systems from continuously improving performance in long-term usage scenarios and from adapting to changes in user behavior.

[0005] In summary, it is evident that previous technologies have long suffered from the inability to personalize ad selection based on different user behaviors, the inability to conduct detailed analysis of ad design elements, the inability to adjust ad content in real time based on the latest user interaction results, and the lack of automated learning mechanisms that prevent the continuous optimization of ad performance. Therefore, it is necessary to propose improved technical means to solve this problem. Summary of the Invention

[0006] In view of the problems existing in previous technologies, such as the inability to personalize ad selection based on different user behaviors, the inability to perform detailed analysis of ad design elements, the inability to adjust ad content in real time based on the latest user interaction results, and the lack of an automated learning mechanism that prevents continuous optimization of ad performance, this invention discloses a dynamic banner ad design and adjustment system based on user behavior analysis, wherein:

[0007] First, this work discloses a dynamic banner ad design and adjustment system based on user behavior analysis. This system includes: a bank marketing analysis server, which further includes: a banner ad database, a user database, an interactive behavior analysis module, a personalized banner ad generation module, and a behavior feedback module.

[0008] The banner ad database stores multiple banner ad messages and their corresponding historical interaction behavior information; the user database stores user identification information and user preference information; the interaction behavior analysis module is connected to both the banner ad database and the user database, performing interaction behavior analysis on the historical interaction behavior information of the banner ad messages to calculate interaction behavior metrics, or calculating intent continuation weights based on cross-page behavior sequences to adjust the interaction behavior metrics of the banner ad messages; the personalized banner ad generation module dynamically selects ad content information corresponding to the currently viewed page from the ad dataset based on user preference information corresponding to user identification information, selecting the ad with the highest interaction behavior metric. The system selects the banner ad information corresponding to the highest interactive behavior index based on the adjusted banner ad information, generates personalized banner ads by dynamically selecting the ad content information according to the design configuration of the banner ad information, and integrates the personalized banner ads into the browsing page; and the behavior feedback module collects user identification information on the interaction effect of personalized banner ads, as well as collects cross-page behavior sequences of user identification information across multiple browsing pages, adjusts the selection strategy of dynamically selecting ad content information corresponding to the current browsing page from the self-ad data based on the interaction effect information, and adjusts the design rules of banner ads based on the interaction effect information.

[0009] The system disclosed in this work, as described above, integrates users' historical interaction behavior, preference characteristics, and design element information of different versions of banner ads through the collaborative operation of a banner ad database, a user database, an interactive behavior analysis module, a personalized banner ad generation module, and a behavior feedback module. This allows the system to automatically compare ad content with user behavior characteristics and generate personalized banner ads that meet user needs through dynamic content selection and design configuration. In turn, it provides an ad presentation mechanism that can be continuously adjusted and cyclically optimized.

[0010] Through the aforementioned technical means, this invention can achieve the following effects: dynamically improving the matching degree between banner ads and user preferences, increasing the click-through rate and final conversion rate of banner ads, enhancing the consistency and accuracy of website browsing experience, and enabling the ad presentation logic to automatically learn and continuously optimize based on user behavior. Simple Explanation of the Diagram

[0011] Figure 1 shows a system block diagram of the dynamic banner ad design and adjustment system based on user behavior analysis. Figures 2A to 2C illustrate the dynamic banner ad design and adjustments based on user behavior analysis in this creation. Figure 3 illustrates a personalized banner ad design and adjustment based on user behavior analysis, representing the dynamic banner ad design and adjustments in this project. Figures 4A and 4B illustrate the flowcharts for the design and adjustment of dynamic banner ads based on user behavior analysis in this creation. Figure 5 illustrates the computer system architecture for the design and adjustment of dynamic banner ads based on user behavior analysis in this project. Implementation

[0012] The following will describe in detail the implementation of this invention with reference to the drawings and embodiments, so that you can fully understand how this invention uses technical means to solve technical problems and achieve technical effects and implement it accordingly.

[0013] The following section will first explain the dynamic banner ad design and adjustment system based on user behavior analysis disclosed in this work, and please refer to "Figure 1". "Figure 1" is a system block diagram of the dynamic banner ad design and adjustment system based on user behavior analysis in this work.

[0014] First, this work discloses a dynamic banner ad design and adjustment system based on user behavior analysis. This system includes: a bank marketing analysis server 10, which further includes: a banner ad database 11, a user database 12, an interactive behavior analysis module 13, a personalized banner ad generation module 14, and a behavior feedback module 15.

[0015] The bank marketing analysis server 10 can obtain user identity information through bank servers, user mobile devices, etc. The aforementioned user identity information includes, for example, a combination of bank account number and password, financial certificates, etc. This is only an example and is not intended to limit the application scope of this invention.

[0016] The banner ad database 11 of the bank marketing analysis server 10 stores multiple banner ad information and corresponding historical interaction behavior information. Specifically, the aforementioned historical interaction behavior information is the behavioral statistics continuously written back and accumulated by the bank marketing analysis server 10 after the banner ad is actually exposed on the website page. The historical interaction behavior information includes, but is not limited to: impression count, actual click count, click-through rate (CTR), hover time, scrolling dwell time, number of times the application process is imported (such as the number of times the online application page is entered after clicking), number of completed applications, conversion rate, and interaction indicators aggregated according to user identity information or customer group segmentation conditions (such as: CTR of new customers, conversion rate of customers with specific risk levels, etc.). This is only an example for illustration and is not intended to demonstrate the application scope of this work.

[0017] In addition, historical interaction behavior information can also record the performance indicators of each version of banner ads during different display periods, such as time-series interaction data on a daily, weekly, or monthly basis, for the bank marketing analysis server 10 to conduct time-dimensional performance analysis and version optimization decisions. Through the multiple banner ad information and corresponding historical interaction behavior information stored in the banner ad database 11, the bank marketing analysis server 10 can conduct detailed comparisons and evaluations of the design and placement effectiveness of each version of banner ads, serving as the basis for subsequent automated adjustments to banner ad content or prioritizing exposure of high-performing versions.

[0018] Please refer to Figures 2A through 2C. Figures 2A through 2C illustrate the dynamic banner ad design and adjustments based on user behavior analysis in this work. Figures 2A through 2C show different design configurations of banner ad 201 with the same ad content. In Figure 2A, the text content of banner ad 201 is 24 pixels and has an arrow icon for "Apply Now". In Figure 2B, the text content is 20 pixels and does not have an arrow icon; instead, it presents "Apply Now" as a hyperlink. In Figure 2C, the text content is 16 pixels and uses a rectangle icon to show the details. Please click here for more information. These are just examples and do not limit the application scope of this work.

[0019] In addition, each version can be customized with different background color blocks, gradient effects, theme image styles, font weight, or spacing adjustments to enhance ad readability and visual hierarchy. Design versions with higher contrast, softer, or brand-identifiable color schemes can also be selected based on user preference analysis to suit different users' visual habits. Furthermore, banner ad versions can incorporate different types of CTA interactive blocks, such as action buttons with rounded corners, promotional emphasis labels with shadow effects, or dynamic gradient prompts whose brightness changes with scrolling position, to attract user attention and encourage further clicks. The most suitable layout can also be automatically switched based on the display scenario (e.g., desktop version, mobile version, dark mode, or bright mode) to maintain visual consistency across different interfaces. Through these diverse design configurations, the interaction differences between versions and different user groups can be collected and analyzed, providing a richer and more detailed foundation for subsequent behavioral analysis models and ad optimization decisions. This is merely an example and does not limit the application scope of this work.

[0020] It is worth noting that banner ads can be designed based on the following design rules, which include, but are not limited to: layout rules, text presentation rules, CTA design rules, visual consistency rules, etc. Layout rules include, for example: image on the left and text on the right, text above image, full-page background image, and centered CTA; text presentation rules include, for example: the main title must be no more than 10 characters, financial products must include digital offers (e.g., 3% cashback), and the subtitle must be placed within two lines below the text block, etc.; CTA design rules include, for example: the CTA must be placed on the bottom right or on a color block, the clickable area must meet the minimum touch size, and the action-oriented words must correspond to the product category (e.g., credit cards should correspond to "Apply Now"; funds should correspond to "Learn More," etc.); visual consistency rules include, for example: the color scheme must match the user's preferred primary color, and the image style must match the user's preferences (people, illustrations, real photos, etc.). These are just examples and do not limit the application scope of this creation.

[0021] The user database 12 of the bank marketing analysis server 10 stores user identification information and user preference information. Specifically, the aforementioned user identification information provides identification for different users. User identification information includes, for example, combinations of bank account numbers and passwords, unique identifiers (e.g., ID card number, bank account number, etc.), financial certificates, etc. These are merely examples and do not limit the application scope of this invention. The aforementioned user preference information includes, but is not limited to, preferred ad types, interaction tendency parameters, preference segmentation information, etc. Preferred ad types include, for example, preference for investment products, preference for credit card rewards, preference for loan products, preference for financial knowledge articles, etc. Interaction tendency parameters include, for example, preferred click time periods (e.g., morning, noon, evening, specific time periods, etc.), preferred device types (e.g., iOS devices, Android devices, etc.), interaction performance in App / Web environments, etc. Preference segmentation information includes, for example, silent users, actively interactive users, users who prefer high-information-volume ads, users who prefer concise marketing language, etc. These are merely examples and do not limit the application scope of this invention.

[0022] The interactive behavior analysis module 13 performs interactive behavior analysis on the historical interactive behavior information of banner ad information to calculate interactive behavior indicators. The interactive behavior analysis module 13 first retrieves the historical interactive behavior information of a specific banner ad from the banner ad database and performs preprocessing on it, such as: time-weighting the click data of different periods, standardizing the browsing dwell time according to the device type, filtering abnormal operations (such as bot traffic, automatic resetting behavior), etc. These are just examples and do not limit the application scope of this invention. Next, it calculates the feature values ​​of each interactive situation in the preprocessed historical interactive behavior information, and then inputs each feature value into the behavior analysis model to analyze and calculate the interactive behavior indicators. The aforementioned behavior analysis model is, for example, a logistic regression model, a gradient boosting model (e.g., XGBoost), a statistical model calculated by weighting, etc. These are just examples and do not limit the application scope of this invention.

[0023] Specifically, assuming the interactive behavior analysis module 13 uses a weighted statistical model as its analysis model, this model calculates the value of each interactive behavior in the historical interactive behavior information by multiplying it by the corresponding weight value and then summing them up. This yields the interactive behavior indicators for the historical interactive behavior information. For example, assuming the historical interactive behavior information includes a click-through rate of "4.2%", an effective dwell time of "3.8 seconds (standardized to 0.62)", an interaction depth of "0.41", a conversion rate after click of "2.1%", and a group matching degree of "0.73", the click-through rate will be calculated as follows: The weights for click-through rate (CTR) are "0.30", effective dwell time is "0.25", interaction depth is "0.15", post-click conversion rate is "0.10", and group matching degree is "0.20". The calculated interaction behavior index is "0.3682" (i.e., calculated as 0.042*0.30+0.62*0.25+0.41*0.15+0.021*0.10+0.73*0.20). This is only an example and is not intended to limit the application scope of this work. The interaction behavior analysis module 13 will use 0.3682 as the interaction behavior index of this banner ad and write it back to the database for subsequent ad selection and automatic optimization processes.

[0024] Next, the personalized banner ad generation module 14 dynamically selects ad content information corresponding to the currently viewed page from the ad dataset based on user preference information corresponding to user identification information. It selects the banner ad information corresponding to the highest interaction behavior index and generates a personalized banner ad 21 using the banner ad information design configuration. In this embodiment, assuming the interaction behavior index of the banner ad information presented in "Figure 2A" is "0.487", the interaction behavior index of the banner ad information presented in "Figure 2B" is "0.321", and the interaction behavior index of the banner ad information presented in "Figure 2C" is "0.368", it will select the banner ad information presented in "Figure 2A" with an interaction behavior index of "0.487". The dynamically selected advertising content information is generated as a personalized banner ad 21 based on the design and configuration of the banner ad information presented in "Figure 2A". The personalized banner ad 21 has a text size of 24 and an arrow icon for immediate application. The personalized banner ad 21 is then integrated into the browsing page 20. For a diagram of the personalized banner ad 21, please refer to "Figure 3". "Figure 3" is a schematic diagram of the personalized banner ad design and adjustment based on user behavior analysis. The personalized banner ad generation module 14 dynamically selects advertising content information corresponding to the current website page browsed from the advertising dataset based on user preference information corresponding to user identification information, so that the banner ad displayed on the user's website page is highly consistent with their preferences, browsing context and needs.

[0025] The aforementioned personalized banner ad generation module 14 dynamically selects ad content information corresponding to the currently viewed page from the central ad data. It first selects the ad category based on the currently viewed page. That is, when browsing a credit card introduction page, it prioritizes credit card ads, and when browsing a deposit and loan page, it prioritizes loan or high-interest deposit ads, etc. This is only an example and is not intended to limit the application scope of this creation.

[0026] With the personalized banner ad generation module 14, website pages can automatically display personalized banner ads 21 that match user preferences, browsing context and behavioral characteristics, so as to dynamically improve banner ad interaction rate, enhance browsing experience consistency and strengthen the accuracy of digital marketing.

[0027] The behavior feedback module 15 collects user identification information and interaction effectiveness information of personalized banner ads. Based on the interaction effectiveness information, it adjusts the selection strategy of dynamically selecting ad content information corresponding to the currently viewed page from the self-ad data set, and adjusts the design rules of banner ads based on the interaction effectiveness information, thereby continuously optimizing the presentation effect of personalized ads.

[0028] The Behavioral Feedback Module 15 collects user identification information and interaction effectiveness information for personalized banner ads. Interaction effectiveness information includes, but is not limited to: number of impressions, number of clicks, click-through rate, mouse dwell time, whether the application process is entered, number of traffic redirects, final conversion rate, interaction time (e.g., morning, afternoon, late night, etc.), and response device (mobile phone, desktop, tablet, etc.). This is only an example and is not intended to limit the application scope of this creation.

[0029] The Behavioral Feedback Module 15 adjusts the selection strategy of advertising content information corresponding to the currently viewed page based on interactive performance information from the self-advertising dataset. This includes, but is not limited to, dynamically adjusting content weights and adjusting strategies based on time periods or devices. The Behavioral Feedback Module 15 dynamically adjusts the weights of different types of content based on personalized advertising performance. For example, if the CTR of a credit card ad is high but the CTR of a fund-related ad is low, the Behavioral Feedback Module 15 will increase the priority weight of credit card content in the user's identity information. If the version with a title containing monetary information increases the CTR of the user's identity information by 30%, the Behavioral Feedback Module 15 will increase the ranking coefficient of this type of content in subsequent content selection. The Behavioral Feedback Module 15 also adjusts strategies based on time periods or devices based on personalized advertising performance. For example, if the click-through rate is particularly high when users use their mobile phones at night, the Behavioral Feedback Module 15 increases the exposure frequency of personalized ads during nighttime hours and prioritizes the use of short ad templates suitable for mobile layouts. This is merely an example and does not limit the application scope of this invention.

[0030] Behavioral Feedback Module 15 adjusts the design rules of banner ads based on interaction performance information, making the generated banner ads more consistent with user identification information. These adjustments include, but are not limited to: color scheme adjustments, CTA adjustments, text length and layout adjustments, image style adjustments, etc. For example, color scheme adjustments: when the CTR of a high-contrast color-coded banner ad is significantly higher than that of a monochrome banner ad, Behavioral Feedback Module 15 adjusts the banner ad design rules to increase the priority of using high-contrast color-coded templates for subsequent user identification information. CTA adjustments: for example, when the user immediately... The click-through rate of the "Apply" button is 3 times higher than that of "Learn More". Behavioral Feedback Module 15 is adjusted to use an action-oriented CTA for the user identification information. For example, when the CTR is significantly higher in the short title version, Behavioral Feedback Module 15 is adjusted to prioritize generating the short title version and avoid using longer text in subsequent versions. For example, when the "People Photo Background" version receives the best response, Behavioral Feedback Module 15 is adjusted to increase the probability of using the People Photo template in the banner ad for the user identification information. This is only an example and is not intended to limit the application scope of this creation.

[0031] Next, the operation process of this creation will be explained below. Please also refer to Figure 4A and Figure 4B, which show the flowchart of the dynamic banner ad design and adjustment based on user behavior analysis.

[0032] First, the bank marketing analysis server pre-establishes a banner ad database storing multiple banner ad information and corresponding historical interaction behavior information (step 301); next, the bank marketing analysis server pre-establishes a user database storing user identification information and user preference information (step 302); next, the bank marketing analysis server performs interaction behavior analysis on the historical interaction behavior information of the banner ad information to calculate interaction behavior indicators (step 303); next, the bank marketing analysis server dynamically selects ad content information corresponding to the currently viewed page from the ad dataset based on the user preference information corresponding to the user identification information (step 304); then, the bank marketing analysis server... The marketing analysis server selects the banner ad information corresponding to the highest interactive behavior index, generates a personalized banner ad by dynamically selecting the ad content information according to the design configuration of the banner ad information, and integrates the personalized banner ad into the browsing page (step 305); then, the bank marketing analysis server collects the user identification information interaction effectiveness information of the personalized banner ad (step 306); then, the bank marketing analysis server adjusts the selection strategy of dynamically selecting the ad content information corresponding to the currently browsing page in the self-ad data based on the interaction effectiveness information (step 307); and finally, the bank marketing analysis server adjusts the design rules of the banner ad based on the interaction effectiveness information (step 308).

[0033] Please refer to Figure 5, which illustrates the computer system architecture for the design and adjustment of dynamic banner ads based on user behavior analysis in this invention. It should be noted that the computer system 400 of the electronic device shown in Figure 5 is merely an example and should not be construed as limiting the functionality or scope of this invention.

[0034] As shown in Figure 5, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to programs stored in Read-Only Memory (ROM) 402 or programs loaded from Storage Unit 408 into Random Access Memory (RAM) 403, such as executing the methods described in the above embodiments. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via bus 404. An Input / Output (I / O) interface 405 is also connected to bus 404.

[0035] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers, etc.; a storage section 408 including a hard drive, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as magnetic disks, optical discs, magneto-optical disks, semiconductor memory, etc., are installed on the drive 410 as needed so that computer programs read from them can be installed into the storage section 408 as needed.

[0036] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including computer code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable media 411. When the computer program is executed by the central processing unit (CPU) 401, it performs various functions defined in the system of the present invention.

[0037] It should be noted that the computer-readable media shown in this embodiment can be a computer-readable signal media, a computer-readable storage media, or any combination thereof. Computer-readable storage media can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), electronically erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical memory devices, magnetic memory devices, or any suitable combination thereof. In this invention, computer-readable signal media can include data signals propagated in a baseband frequency or as part of a carrier wave, carrying computer-readable computer programs. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. Computer programs contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0038] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in the flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0039] The units described in this embodiment can be implemented in software or hardware, and can also be located in a processor. The names of these units do not necessarily limit the specific unit itself. Therefore, the technical solution according to this embodiment can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to this embodiment.

[0040] In summary, through the collaborative operation of the banner ad database, user database, interactive behavior analysis module, personalized banner ad generation module, and behavior feedback module, the system integrates users' historical interactive behavior, preference characteristics, and design element information of different versions of banner ads. This enables the system to automatically compare ad content with user behavior characteristics and generate personalized banner ads that meet user needs through dynamic content selection and design configuration, thereby providing an ad presentation mechanism that can be continuously adjusted and cyclically optimized.

[0041] This technology can solve the problems of previous technologies, such as the inability to personalize ad selection based on different user behaviors, the inability to conduct detailed analysis of ad design elements, the inability to adjust ad content in real time based on the latest user interaction results, and the lack of an automated learning mechanism that prevents continuous optimization of ad performance. It can achieve the following effects: dynamically improve the matching degree between banner ads and user preferences, increase the click-through rate and final conversion rate of banner ads, enhance the consistency and accuracy of website browsing experience, and enable the ad presentation logic to automatically learn and continuously optimize based on user behavior.

[0042] While the embodiments disclosed in this invention are as described above, the content is not intended to directly limit the scope of patent protection for this invention. Anyone skilled in the art to which this invention pertains may make minor modifications in form and detail without departing from the spirit and scope disclosed herein. The scope of patent protection for this invention shall still be determined by the appended claims.

[0043] 10: Bank Marketing Analytics Server 11: Banner Advertisement Database 12: User Database 13: Interactive Behavior Analysis Module 14: Personalized Banner Ad Generation Module 15: Behavioral Feedback Module 20: Browse Page 201: Banner Advertisement 21: Personalized Banner Ads 301-308: Steps 400: Computer System 401: CPU 402:ROM 403: RAM 404: Busbar 405:I / O interface 406: Input section 407: Output Section 408: Storage Section 409: Communication Section 410: Driver 411: Uninstallable media

Claims

1. A dynamic banner ad design and adjustment system based on user behavior analysis, the system comprising: a bank marketing analysis server, the bank marketing analysis server further comprising: a banner ad database storing multiple banner ad information and corresponding historical interaction behavior information; a user database storing user identification information and user preference information; and an interaction behavior analysis module connected to the banner ad database and the user database, performing interaction behavior analysis on the historical interaction behavior information of the banner ad information to calculate an interaction behavior index, or calculating an intent continuation weight based on a cross-page behavior sequence to adjust the interaction behavior index of the banner ad information; A personalized banner ad generation module, connected to the interactive behavior analysis module, dynamically selects ad content information corresponding to a currently viewed page from an ad dataset based on user preference information corresponding to user identification information. It selects the banner ad information corresponding to the highest interactive behavior index, or selects the banner ad information corresponding to the highest interactive behavior index based on the adjusted interactive behavior index of the banner ad information. The dynamically selected ad content information is then used to generate a personalized banner ad according to the design configuration of the banner ad information, and the personalized banner ad is integrated into the viewed page. A behavior feedback module, connected to the personalized banner ad generation module, collects interactive performance information of the user identification information on the personalized banner ad, and collects the cross-page behavior sequence of the user identification information across multiple viewed pages. Based on the interactive performance information, it adjusts the selection strategy of dynamically selecting the ad content information corresponding to the currently viewed page from the ad dataset, and adjusts the design rules of the banner ad based on the interactive performance information.

2. The dynamic banner ad design and adjustment system based on user behavior analysis as described in Request 1, wherein the personalized banner ad generation module dynamically selects ad content information corresponding to the currently viewed page from the ad dataset, first selecting the ad category based on the currently viewed page, and then selecting the best ad content based on the user preference information and the historical interaction behavior.

3. The dynamic banner ad design and adjustment system based on user behavior analysis as described in Request 1, wherein the banner ad design rules include layout rules, text presentation rules, CTA design rules, and visual consistency rules.

4. The dynamic banner ad design and adjustment system based on user behavior analysis as described in Request 1, wherein the historical interaction behavior information includes exposure count, actual click count, click-through rate, mouse dwell time, scroll dwell time, number of times the application process is imported, number of completed applications, conversion rate, and interaction metrics aggregated according to user identity information or customer segmentation conditions.

5. The dynamic banner ad design and adjustment system based on user behavior analysis as described in claim 1, wherein the user preference information includes preferred ad type, interaction tendency parameters, and preference segmentation information.

Images