A CMF-based interactive display method and system for graphic and text advertisements

Abstract

The present invention discloses a method and system for interactive display of graphic and text advertisements based on CMF, which specifically relates to the field of digital advertising technology. The method and system include the following steps: determining the shortest time benchmark required for optimization when generating interactive display of graphic and text advertisements, real-time monitoring and recording each optimization time, analyzing data, preliminarily identifying hidden dangers of imbalance between display performance and interaction quality, performing abnormal analysis and processing after identifying the hidden dangers, establishing an interactive display balance recognition model and dividing interactive display types into high-demand interactive displays and low-demand interactive displays, and using a genetic algorithm to perform secondary optimization on the performance and interactivity of the display for high-demand interactive displays, so that the display is reclassified as low-demand interactive displays; the present invention can accurately identify the imbalance between display performance and interaction quality, use the interactive display balance recognition model, combine the display quality index and the interaction quality index, comprehensively evaluate the balance of advertisement display, and adaptively adjust the optimization strategy.

Description

Technical Field

[0001] The present invention relates to the field of digital advertising technology, and more particularly to a method and system for interactively displaying graphic and text advertisements based on CMF. Background Art

[0002] CMF-based interactive display of graphic and text ads refers to the use of a content management framework to create and manage advertising content consisting of images and text, and enhance the user experience through interactive elements. CMF provides a flexible platform that enables developers to efficiently organize and edit advertising content while supporting the integration of multiple media formats. With CMF, advertising content can be easily updated and maintained, ensuring the timeliness and relevance of advertising information.

[0003] In this display method, interactive elements, such as clicks, slides, and animations, play a key role in attracting user attention and increasing engagement. Through these interactive designs, users not only see static ad content but also interact with it, creating a more vivid and personalized experience. This approach not only improves ad visibility and memorability but also enables the collection of user behavior data, providing valuable feedback for optimizing advertising strategies.

[0004] Existing technologies have the following shortcomings: high-quality images and complex interactive effects can lead to slow page loading, especially on mobile devices. This not only affects the user experience but can also lead to user churn. Performance optimization requires finding a balance between maintaining visual quality and user interaction. Furthermore, different users have different interaction requirements. A standardized performance optimization approach based on pre-defined conditions wastes resources and can even reduce the user experience. Therefore, we propose a method and system for interactive display of graphic and text advertisements based on CMF. Summary of the Invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for interactively displaying graphic and text advertisements based on CMF, characterized by comprising the following steps:

[0007] Step 1: Determine the minimum optimization time required to generate interactive display images and text ads. During the display optimization process, monitor and record the actual optimization time spent on each display in real time. Analyze the recorded actual optimization time data to initially identify potential risks of imbalance between display performance quality and interactive quality during the optimization process.

[0008] Step 2: When the optimization operation is initially identified as having a hidden danger of imbalance between display performance quality and interaction quality, characteristic parameter information after the optimization operation is obtained, abnormality analysis is performed on the obtained information, and an interactive display balance identification model is established based on the abnormality analysis data;

[0009] Step 3: Using the interactive balance identification model, the interactive display types are divided into high-demand interactive displays and low-demand interactive displays.

[0010] Step 4: For high-demand interactive displays, use a genetic algorithm to perform secondary optimization on the performance and interactivity of the interactive displays, so that they are reclassified as low-demand interactive displays.

[0011] In a preferred embodiment, the steps for preliminarily identifying the hidden danger of imbalance between performance quality and interaction quality in the optimization operation are as follows:

[0012] During the interactive display of graphic and text ads, the start and end timestamps of each optimization operation are monitored and collected in real time. The difference between the end and start timestamps is then taken as the actual optimization time for each optimization operation.

[0013] Obtain the actual optimization time of m consecutive optimization operations within a preset time window, establish a data set, and then calculate the mean optimization time and the standard deviation of the optimization time based on the actual optimization time in the data set;

[0014] The mean threshold and standard deviation threshold of optimization time are set based on the content of the interactive display of graphic and text advertisements. If the mean optimization time exceeds the preset mean threshold of optimization time or the standard deviation of optimization time exceeds the preset threshold of optimization time, it is preliminarily identified that there is a hidden danger of imbalance between display performance quality and interaction quality in the optimization operation.

[0015] In a preferred embodiment, when it is preliminarily identified that the optimization operation has the hidden danger of imbalance between display performance quality and interaction quality, characteristic parameter information after the optimization operation is obtained, and the characteristic parameter information includes display information and interaction information. After abnormal analysis and processing of the display information and the interaction information respectively, the display quality index and the interaction quality index are obtained. Then, an interactive display balance identification model is established based on the display quality index and the interaction quality index, and an interactive display balance coefficient is generated. The interactive display balance coefficient is used to evaluate the balance between interaction and display during the interactive display of graphic and text advertisements.

[0016] In a preferred embodiment, an interactive display balance coefficient output from an interactive display balance identification model is obtained, and the interactive display balance coefficient is compared and analyzed with a preset interactive display balance requirement threshold. If the interactive display balance coefficient is greater than or equal to the preset interactive display balance requirement threshold, the interactive display type is classified as a high-demand interactive display; if the interactive display balance coefficient is less than the preset interactive display balance requirement threshold, the interactive display type is classified as a low-demand interactive display.

[0017] In a preferred embodiment, for high-demand interactive presentations, using a genetic algorithm to perform secondary optimization on the performance and interactivity of the interactive presentation refers to:

[0018] Obtain multiple preset display parameters and interaction parameters, summarize the display parameters and interaction parameters obtained each time into a set of parameter combinations, determine the initialization population, each individual represents a set of parameter combinations, design the fitness function, and perform selection, crossover, mutation, and replacement in sequence, and perform iterative processing until the termination condition is met.

[0019] In a preferred embodiment, satisfying the termination condition means that the interactive presentation type is reclassified as a low-demand interactive presentation.

[0020] In a preferred embodiment, abnormal analysis is performed on the display information to obtain a display quality index, which is:

[0021] Collect the display information of the preset time window to form a display parameter data set. Use the interquartile range method to remove outliers, and then standardize the data so that the mean of each parameter is 0 and the standard deviation is 1. The data standardization formula is: X is the original data, μ is the mean, σ is the standard deviation, and the abnormality A of each parameter is calculated. The abnormality A is the degree of deviation of each standardized parameter from its mean. Ai,j is the abnormality of the jth parameter in the i-th data sample, Xi,j is the standardized data, μj and σj are the mean and standard deviation of the j-th parameter respectively, and then the parameter abnormality of all samples is summed to obtain the comprehensive abnormality Ai of each sample, and then the display quality index DQI is calculated. DQI is the comprehensive display quality index of the entire dataset, n is the number of samples, and Abaseline is the preset baseline anomaly.

[0022] In a preferred embodiment, the interaction information is subjected to abnormal analysis to obtain an interaction quality index, which is:

[0023] Collect interaction information in a preset time window to form an interaction parameter dataset. Standardize the raw data in the interaction parameter dataset to obtain an interaction parameter processing set. Then, assign weights to the feature indicators corresponding to each interaction parameter according to their importance. Finally, calculate the interaction quality index through weighted polynomial regression: HQI is the interaction quality index, JHi,normal is the interaction parameter numbered i after normalization, and wi is the weight coefficient assigned to JHi,normal.

[0024] In a preferred embodiment, establishing an interactive display balance recognition model through the display quality index and the interaction quality index means: obtaining the display quality index DQI and the interaction quality index HQI as input data of the interactive display balance recognition model, using the interactive display balance coefficient as output data of the interactive display balance recognition model, training the interactive display balance recognition model, and when the preset performance indicators meet the preset requirements, the interactive display balance recognition model is completed.

[0025] In a preferred embodiment, a CMF-based interactive display system for graphic and text advertisements includes a recognition module, an auxiliary model building module, a type classification module, and a secondary optimization module;

[0026] The identification module is used to determine the minimum time benchmark required for optimizing interactive display of graphic ads. During the display optimization process, the module monitors and records the actual optimization time spent on each display optimization in real time. The module analyzes the recorded actual optimization time data to preliminarily identify potential risks of imbalance between display performance quality and interactive quality during the optimization operation.

[0027] The auxiliary model building module is used to obtain characteristic parameter information after the optimization operation when it is initially identified that there is a hidden danger of imbalance between display performance quality and interaction quality in the optimization operation, perform abnormal analysis on the obtained information, and establish an interactive display balance identification model based on the data after abnormal analysis;

[0028] The type classification module is used to classify interactive display types into high-demand interactive displays and low-demand interactive displays based on the output results of the display interaction balance recognition model;

[0029] The secondary optimization module is used to perform secondary optimization on the performance and interactivity of interactive displays for high-demand interactive displays using genetic algorithms, so that they are reclassified as low-demand interactive displays.

[0030] The technical effects and advantages of the present invention are as follows:

[0031] By calculating the display quality index (DQI) and the interaction quality index (HQI), the present invention can accurately evaluate the display effect of graphic advertisements and the user interaction experience, thereby providing data support for subsequent optimization and improving the comprehensive quality of display and interaction; the present invention can monitor the time of each optimization operation in real time during the display of graphic advertisements, identify the hidden dangers of imbalance in display performance quality and interaction quality, and make timely adjustments and optimizations to ensure the continuous optimization of advertising display effects and user experience.

[0032] Through data analysis and model recognition, the present invention can accurately identify the imbalance between display performance and interaction quality, so as to take targeted optimization measures to improve the overall performance of advertisements. By using the interactive display balance recognition model, combined with the display quality index and the interaction quality index, the balance of advertisement display is comprehensively evaluated to ensure that the user's interactive experience is not sacrificed while improving the display effect, thereby achieving multi-dimensional balanced optimization.

[0033] The present invention adaptively adjusts the optimization strategy according to the changes in display and interaction data through the set machine learning model and genetic algorithm, improves the optimization efficiency and effect, and realizes the intelligent management and optimization of advertising display. By optimizing the display performance and interaction quality, it ensures that the advertising content can be loaded and responded quickly, and the visual effect and interactive experience are good, thereby improving user satisfaction and stickiness, and bringing higher advertising effects and conversion rates to advertisers. Through real-time monitoring and precise optimization, the present invention can reduce the waste of resources caused by poor performance and visual effects, reduce the cost of advertising optimization, and improve the economic benefits of advertising operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0035] Figure 1 This is a schematic diagram of a CMF-based interactive display method for graphic and text advertisements in the present invention.

[0036] Figure 2 This is a schematic diagram of a CMF-based interactive display system for graphic and text advertisements in the present invention. DETAILED DESCRIPTION

[0037] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0038] Reference Figure 1 - Figure 2 The following examples were obtained:

[0039] Example 1: A method for interactively displaying graphic and text advertisements based on CMF, characterized by comprising the following steps:

[0040] Step 1: Determine the minimum time benchmark required for optimization when generating interactive displays of graphic ads. During the display optimization process, monitor and record the actual optimization time spent on each display optimization in real time. Analyze the recorded actual optimization time data to preliminarily identify the hidden dangers of imbalance between display performance quality and interaction quality in the optimization operation. In the interactive display of graphic ads based on CMF, optimization refers to improving the loading speed and interactive performance of ad content through technical means and design adjustments, while maintaining or enhancing its visual effects and user experience. The optimization process includes measures such as image compression, code streamlining, the use of content distribution networks, delayed loading, and animation performance optimization to ensure that ads can run smoothly on different devices and network environments. The optimization mentioned here is a basic optimization strategy used to cater to the interactive display needs of the general population. However, due to the differences in interactors, the optimization strategy also needs to be changed. The hidden danger of imbalance between display performance quality and interaction quality means that the basic optimization strategy at this time can no longer meet the needs of the interactor.

[0041] Step 2: When it is preliminarily identified that the optimization operation has the hidden danger of imbalance between display performance quality and interaction quality, obtain the characteristic parameter information after the optimization operation, perform abnormal analysis on the obtained information, and establish an interactive display balance identification model based on the data after abnormal analysis.

[0042] Step 3: Use the display interaction balance identification model to classify interactive display types into high-demand interactive displays and low-demand interactive displays. High-demand interactions have high performance requirements: interactions that require fast response and high frame rates, such as smooth animations and real-time data updates. High user attention: interactions that are frequently used by users and have a significant impact on user experience and advertising effectiveness, such as sliding switches of the main visual image and clicking core buttons. Low-demand interactions have low performance requirements: interactions that do not require immediate response or can tolerate a certain delay, such as the expansion of secondary information and background animations. Low user attention: interactions that are occasionally used by users and have little impact on the overall user experience and advertising effectiveness, such as scrolling of secondary information and decorative animations. High-demand interactive displays require secondary optimization.

[0043] Step 4: For high-demand interactive displays, use a genetic algorithm to perform secondary optimization on the performance and interactivity of the interactive displays, so that they are reclassified as low-demand interactive displays.

[0044] The steps for preliminarily identifying the hidden danger of imbalance between display performance quality and interactive quality in optimization operations are as follows: During the interactive display of graphic and text ads, the start and end timestamps of each optimization operation are monitored and collected in real time, and the difference between the end and start timestamps is obtained as the actual optimization time of each optimization operation; the actual optimization times of m consecutive optimization operations within a preset time window are obtained, a data set is established, and then the mean and standard deviation of the optimization time are calculated based on the actual optimization times in the data set;

[0045] Based on the content of interactive graphic and text ads, mean and standard deviation thresholds for optimization time are set. If the mean optimization time exceeds the preset mean optimization time threshold or the standard deviation exceeds the preset optimization time threshold, this indicates a potential imbalance between display performance and interaction quality in the optimization operation. During the interactive display of graphic and text ads based on CMF, the display effect is optimized, the timestamp of each optimization operation is monitored and collected in real time, and the actual optimization time is calculated. If the mean or standard deviation of the optimization time exceeds the preset threshold, it indicates unstable optimization time. Instability in optimization time can affect the user experience, as users may experience fast interactions at some times and slow interactions at others, resulting in an inconsistent experience. By calculating the mean and standard deviation of the optimization time and comparing them with the preset thresholds, it is possible to initially identify potential imbalances between display performance and interaction quality in the optimization operation. If the mean and standard deviation of the optimization time exceed the preset threshold, it may indicate that the current optimization strategy is over-optimizing or under-optimizing certain aspects (such as performance or interaction quality), resulting in an imbalance between the two. Specifically, it is manifested as follows: Display performance quality: If the display performance quality is poor, users may experience slow page loading, animation lag, or even display errors, which will directly affect the user's visual experience; Interaction quality: If the interaction quality is poor, users may encounter problems such as unresponsive clicks, touch delays, and operational errors, which will reduce the user's operational fluency and satisfaction. The preset mean threshold and standard deviation threshold for optimization time indicate that there are clear standards for the expected effects of the optimization operation. If the actual optimization time fails to meet the preset standards, it means that the current optimization operation is insufficiently effective and the required optimization work cannot be completed within a reasonable time. Further adjustments and improvements to the optimization strategy may be required to better balance the display performance quality and interaction quality.

[0046] When it is preliminarily identified that the optimization operation has the hidden danger of imbalance between display performance quality and interaction quality, characteristic parameter information after the optimization operation is obtained, and the characteristic parameter information includes display information and interaction information. After performing abnormal analysis on the display information and the interaction information respectively, a display quality index and an interaction quality index are obtained. Then, an interactive display balance identification model is established based on the display quality index and the interaction quality index, and an interactive display balance coefficient is generated. The interactive display balance coefficient is used to evaluate the balance between interaction and display during the interactive display of graphic and text advertisements, and the interactive display balance coefficient output from the interactive display balance identification model is obtained. The interactive display balance coefficient is compared and analyzed with a preset interactive display balance requirement threshold. If the interactive display balance coefficient is greater than or equal to the preset interactive display balance requirement threshold, the interactive display type is classified as a high-demand interactive display. If the interactive display balance coefficient is less than the preset interactive display balance requirement threshold, the interactive display type is classified as a low-demand interactive display.

[0047] For high-demand interactive displays, using a genetic algorithm to perform secondary optimization on the performance and interactivity of the interactive display refers to: obtaining multiple preset display parameters and interaction parameters, summarizing the display parameters and interaction parameters obtained each time into a set of parameter combinations, determining the initialization population, each individual representing a set of parameter combinations, designing a fitness function, and performing selection, crossover, mutation, and replacement in sequence, and iterative processing until the termination condition is met; for example: defining an objective function, combining the performance quality index and the interaction quality index, and considering their weights α and β, calculating the overall fitness F itness, Fitness = α·DQI+β·HQI, where α and β are both not 0, selection operation: using roulette selection or tournament selection to select individuals with high fitness as parent individuals for reproduction, and the present invention can apply roulette selection; crossover operation: performing a crossover operation on the selected parent individuals to generate new offspring. Methods such as single-point crossover, double-point crossover or uniform crossover can be used, and the present invention can apply uniform crossover; mutation operation: mutate some offspring individuals and randomly change their parameter values to increase the diversity of the population and avoid falling into local optimality; population replacement: replace individuals with lower fitness in the old population with newly generated offspring to form a new generation of population. Iterative processing refers to repeated cycles of selection, crossover, mutation, and replacement. Meeting the termination condition means that the interactive display type is reclassified into low-demand interactive display, so that interaction and display reach a balance condition.

[0048] Performing abnormal analysis on display information to obtain a display quality index involves collecting display information within a preset time window to form a display parameter data set. The parameter data set may include load time (LT), image quality (IQ), frame rate (FR), image clarity, color consistency, animation fluency, font and layout correctness, etc. The interquartile range method is used to remove outliers, and then the data is standardized so that the mean of each parameter is 0 and the standard deviation is 1. The data normalization formula is: X is the original data, μ is the mean, σ is the standard deviation, and the abnormality A of each parameter is calculated. The abnormality A is the degree of deviation of each standardized parameter from its mean. Ai,j is the abnormality of the jth parameter in the i-th data sample, Xi,j is the standardized data, μj and σj are the mean and standard deviation of the j-th parameter respectively, and then the parameter abnormality of all samples is summed to obtain the comprehensive abnormality Ai of each sample, and then the display quality index DQI is calculated. DQI is the comprehensive display quality index of the entire dataset, where n is the number of samples and Abaseline is the preset baseline anomaly level. The display quality index (DQI) represents the overall display quality of the entire dataset. A high DQI value indicates good display quality, with minimal deviations from the mean for each parameter and a balanced and stable display. Conversely, a low DQI value indicates a high degree of anomalies and deviations in the display, indicating poor quality and requiring further optimization and improvement.

[0049] The interaction quality index obtained by analyzing and processing the interaction information is:

[0050] Collect interaction information in a preset time window to form an interaction parameter dataset. Standardize the raw data in the interaction parameter dataset to obtain an interaction parameter processing set. Then, assign weights to the feature indicators corresponding to each interaction parameter according to their importance. Finally, calculate the interaction quality index through weighted polynomial regression: HQI stands for the interaction quality index, where JHi and normal are the interaction parameters numbered i after normalization, and wi is the weight coefficient assigned to JHi and normal. The interaction quality index (HQI) is a comprehensive indicator reflecting the overall quality of interactive information. It evaluates the quality and stability of interactive content through normalization of interaction data and weighted polynomial regression calculation. A high HQI value indicates good interaction quality, minimal data deviation, and a good user interaction experience. A low HQI value indicates poor interaction quality, significant data deviation, and a need for improvement in the user interaction experience.

[0051] Establishing an interactive display balance recognition model through the display quality index and the interaction quality index refers to: obtaining the display quality index DQI and the interaction quality index HQI as input data of the interactive display balance recognition model, and using the interactive display balance coefficient as output data of the interactive display balance recognition model, training the interactive display balance recognition model, and when the preset performance indicators meet the preset requirements, the interactive display balance recognition model is constructed, and an appropriate machine learning model is selected, such as linear regression, support vector machine (SVM), and neural network. The present invention exemplifies the selection of a neural network. The preset performance indicator can set the loss function as the mean square error. When the preset requirements are met, the interactive display balance recognition model is constructed. The interactive display balance recognition model uses the display quality index (DQI) and the interaction quality index (HQI) as input data, trains the model through a machine learning method, and predicts the interactive display balance coefficient. When the performance indicators of the model meet the preset requirements, the model can be used to evaluate and optimize the overall balance of the interactive display and improve the user experience.

[0052] Example 2: A CMF-based interactive display system for graphic and text advertisements, comprising a recognition module, an auxiliary model building module, a type classification module, and a secondary optimization module;

[0053] The identification module is used to determine the minimum time benchmark required for optimizing interactive display of graphic ads. During the display optimization process, the module monitors and records the actual optimization time spent on each display optimization in real time. The module analyzes the recorded actual optimization time data to preliminarily identify potential risks of imbalance between display performance quality and interactive quality during the optimization operation.

[0054] The auxiliary model building module is used to obtain characteristic parameter information after the optimization operation when it is initially identified that there is a hidden danger of imbalance between display performance quality and interaction quality in the optimization operation, perform abnormal analysis on the obtained information, and establish an interactive display balance identification model based on the data after abnormal analysis;

[0055] The type classification module is used to classify interactive display types into high-demand interactive displays and low-demand interactive displays based on the output results of the display interaction balance recognition model;

[0056] The secondary optimization module is used to perform secondary optimization on the performance and interactivity of interactive displays for high-demand interactive displays using genetic algorithms, so that they are reclassified as low-demand interactive displays.

[0057] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0058] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0059] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0060] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0061] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A CMF-based interactive display method for graphic and text advertisements, characterized in that: The following steps are involved: Step 1: Determine the minimum optimization time required to generate interactive display images and text ads. During the display optimization process, monitor and record the actual optimization time spent on each display in real time. Analyze the recorded actual optimization time data to initially identify potential risks of imbalance between display performance quality and interactive quality during the optimization process. Step 2: When the optimization operation is initially identified as having a hidden danger of imbalance between display performance quality and interaction quality, characteristic parameter information after the optimization operation is obtained, abnormality analysis is performed on the obtained information, and an interactive display balance identification model is established based on the abnormality analysis data; Step 3: Using the interactive balance identification model, the interactive display types are divided into high-demand interactive displays and low-demand interactive displays. Step 4: For high-demand interactive displays, use a genetic algorithm to perform secondary optimization on the performance and interactivity of the interactive displays, so that they are reclassified as low-demand interactive displays; When it is initially identified that the optimization operation has the potential risk of imbalance between display performance quality and interaction quality, characteristic parameter information after the optimization operation is obtained. The characteristic parameter information includes display information and interaction information. After abnormal analysis and processing of the display information and the interaction information respectively, a display quality index and an interaction quality index are obtained. Then, an interactive display balance identification model is established based on the display quality index and the interaction quality index, and an interactive display balance coefficient is generated. The interactive display balance coefficient is used to evaluate the balance between interaction and display during the interactive display of graphic and text advertisements. Perform abnormal analysis on the display information and obtain the display quality index, which is: Collect the display information of the preset time window to form a display parameter data set. Use the interquartile range method to remove outliers, and then standardize the data so that the mean of each parameter is 0 and the standard deviation is 1. The data standardization formula is: X is the original data, μ is the mean, σ is the standard Difference, calculate the abnormality A of each parameter, which is the degree of deviation of each standardized parameter from its mean. A i , j is the abnormality of the jth parameter in the i-th data sample, X i , j is the standardized data, μj, σj are the mean and standard deviation of the jth parameter respectively, then the parameter abnormality of all samples is summed up to obtain the comprehensive abnormality Ai of each sample, and then the display quality index DQ I is calculated. DQI is the comprehensive display quality index of the entire data set, n is the number of samples, A baseline is the preset baseline abnormality; The interaction quality index obtained by analyzing and processing the interaction information is: Collect interaction information in a preset time window to form an interaction parameter dataset. Standardize the raw data in the interaction parameter dataset to obtain an interaction parameter processing set. Then, assign weights to the feature indicators corresponding to each interaction parameter according to their importance. Finally, calculate the interaction quality index through weighted polynomial regression: HQI is the interaction quality index, JH i , normal is the interaction parameter numbered i after normalization, wi is JH i , the weight coefficient assigned to normal.

2. The interactive display method of graphic and text advertisements based on CMF according to claim 1, characterized in that: The steps to initially identify the hidden danger of imbalance between display performance quality and interaction quality in optimization operations are as follows: During the interactive display of graphic and text ads, the start and end timestamps of each optimization operation are monitored and collected in real time. The difference between the end and start timestamps is then taken as the actual optimization time for each optimization operation. Obtain the actual optimization time of m consecutive optimization operations within a preset time window, establish a data set, and then calculate the mean optimization time and the standard deviation of the optimization time based on the actual optimization time in the data set; The mean threshold and standard deviation threshold of optimization time are set based on the content of the interactive display of graphic and text advertisements. If the mean optimization time exceeds the preset mean threshold of optimization time or the standard deviation of optimization time exceeds the preset standard deviation threshold of optimization time, it is preliminarily identified that there is a hidden danger of imbalance between display performance quality and interaction quality in the optimization operation.

3. The interactive display method of graphic and text advertisements based on CMF according to claim 2, characterized in that: Obtain the interactive display balance coefficient output from the interactive display balance identification model, compare and analyze the interactive display balance coefficient with the preset interactive display balance requirement threshold; if the interactive display balance coefficient is greater than or equal to the preset interactive display balance requirement threshold, classify the interactive display type as a high-demand interactive display; if the interactive display balance coefficient is less than the preset interactive display balance requirement threshold, classify the interactive display type as a low-demand interactive display.

4. The interactive display method of graphic and text advertisements based on CMF according to claim 3, characterized in that: For high-demand interactive displays, using genetic algorithms to perform secondary optimization on the performance and interactivity of interactive displays refers to: Obtain multiple preset display parameters and interaction parameters, summarize the display parameters and interaction parameters obtained each time into a set of parameter combinations, determine the initialization population, each individual represents a set of parameter combinations, design the fitness function, and perform selection, crossover, mutation, and replacement in sequence, and perform iterative processing until the termination condition is met.

5. The interactive display method of graphic and text advertisements based on CMF according to claim 4, characterized in that: Meeting the termination condition means that the interactive display type is reclassified as a low-demand interactive display.

6. The interactive display method of graphic and text advertisements based on CMF according to claim 5, characterized in that: Establishing an interactive display balance recognition model through the display quality index and the interaction quality index means: obtaining the display quality index DQI and the interaction quality index HQI as input data of the interactive display balance recognition model, using the interactive display balance coefficient as output data of the interactive display balance recognition model, training the interactive display balance recognition model, and when the preset performance indicators meet the preset requirements, the interactive display balance recognition model is completed.

7. A CMF-based interactive display system for graphic and text advertisements, based on a CMF-based interactive display method for graphic and text advertisements according to any one of claims 1 to 6, characterized in that: Including recognition module, auxiliary model building module, type classification module, and secondary optimization module; The identification module is used to determine the minimum time benchmark required for optimizing interactive display of graphic ads. During the display optimization process, the module monitors and records the actual optimization time spent on each display optimization in real time. The module analyzes the recorded actual optimization time data to preliminarily identify potential risks of imbalance between display performance quality and interactive quality during the optimization operation. The auxiliary model building module is used to obtain characteristic parameter information after the optimization operation when it is initially identified that there is a hidden danger of imbalance between display performance quality and interaction quality in the optimization operation, perform abnormal analysis on the obtained information, and establish an interactive display balance identification model based on the data after abnormal analysis; The type classification module is used to classify interactive display types into high-demand interactive displays and low-demand interactive displays based on the output results of the display interaction balance recognition model; The secondary optimization module is used to perform secondary optimization on the performance and interactivity of interactive displays for high-demand interactive displays using genetic algorithms, so that they are reclassified as low-demand interactive displays.

Images