A method for processing visual effects

Abstract

This invention discloses a visual effects application processing method, belonging to the field of visual effects processing technology. By decomposing visual effects identifiers into multiple interactive scenarios and combining them with in-depth analysis of user behavior data, it can dynamically identify and understand users' effects preferences and their real-time changes. This analysis can not only accurately evaluate the quality of each effect element, but also generate high-quality fusion guidance information, providing a basis for the optimization of effects processing. Based on the globally optimized effects execution scenario information, the method can update and build a user profile database in real time, improving the system's response speed and personalized service capabilities. The push strategy is optimized by combining the user profile analysis results. This processing method can better meet user needs, improve the accuracy of visual effects content push and optimize user experience, overcoming the problems of static push strategies and low matching in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of visual effects processing technology, and more specifically to a method for visual effects processing. Background Technology

[0002] Visual effects (VFX) are the art of enhancing or creating visual expression through a series of computer-generated imagery (CGI) techniques and traditional filming techniques. VFX is widely used in film, television, video games, and advertising to create impressive visual effects and special effects scenes. With the advancement of technology, the application scope of visual effects has continued to expand, from early simple smoke and explosions to modern complex scenes such as virtual worlds, digitized characters, and surreal effects.

[0003] The existing technology has the following drawbacks:

[0004] In traditional processing methods, the recommendation and push strategies for special effects content usually rely on static rules or relatively simple user behavior analysis. This method is difficult to adapt to the dynamic changes in user needs, resulting in the recommended special effects content often failing to accurately match the user's real-time needs. For example, there is a lack of in-depth analysis of user interaction behavior during push, making it impossible to accurately understand the user's specific preferences for special effects, and it is also impossible to effectively integrate and optimize multiple visual effects elements, resulting in a low degree of matching between special effects content and user needs.

[0005] Based on this, the present invention proposes a visual effects application processing method that can better meet user needs, improve the accuracy of visual effects content push and user experience, and overcome the problems of static push strategy and low matching degree in the prior art. Summary of the Invention

[0006] The purpose of this invention is to provide a visual effect processing method to overcome the shortcomings of the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a visual effect processing method, the processing method comprising the following steps:

[0008] Step S1: Obtain the visual effects identifiers that exist in the current special effects push project;

[0009] Step S2: Decompose the visual effects identifier into several visual effects interaction scenarios, and analyze the effects of each visual effects interaction scenario and its interaction data with users;

[0010] Step S3: Use the special effects content integration algorithm to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion pointing information;

[0011] Step S4: Evaluate the integration of special effects performance with information based on the effect evaluation model, and quantify the quality of each special effects element;

[0012] Step S5: Based on the special effects performance fusion direction information and effect evaluation results, perform special effects optimization processing to generate globally optimized visual effects execution scene fusion direction information;

[0013] Step S6: Utilize the globally optimized visual effects execution scene fusion pointing information to construct the corresponding visual effects user profile library;

[0014] Step S7: Analyze changes in user needs based on the visual effects user profile database and update the push strategy for the current effects push project.

[0015] In a preferred embodiment, special effects are optimized based on the special effects performance fusion direction information and effect evaluation results to generate globally optimized visual effects execution scene fusion direction information, including the following steps:

[0016] Based on the effect evaluation results, combined with the special effects performance and user feedback data, the special effects performance is dynamically adjusted, and each special effects element is weighted and adjusted according to the various dimensions of the special effects evaluation.

[0017] The optimization results of all special effects elements are processed uniformly, and the optimized visual effects execution scene fusion information includes all the adjusted and optimized special effects elements and their relationships with each other;

[0018] Each effect element includes visual effects, trigger condition information, and a description of its coordination with other effects and the impact of changes in user behavior;

[0019] After global optimization, new visual effects execution scene fusion information is generated, including the optimization results of the effects elements, global coordination strategies, and user behavior data.

[0020] In a preferred embodiment, a corresponding visual effects user profile library is constructed using globally optimized visual effects execution scene fusion pointing information, including the following steps:

[0021] User profiles are used to describe the relationship between users and special effects, including user preferences, user behavior, and special effect reactions;

[0022] The optimized visual effects execution scenario is integrated and mapped with the information and the user's actual interaction data. Whenever the user interacts with a certain effect, the relevant information of the effect is recorded and matched with the user's behavior data. Each element in the optimized visual effects execution scenario is matched with the user's preferences and behaviors.

[0023] The user profile database is stored in a hierarchical structure, in relational databases, non-relational databases, or graph databases;

[0024] When storing data, a unique profile is created for each user, which includes the user's special effects preferences, behavior records, and interaction history.

[0025] In a preferred embodiment, the push strategy for the current special effects push project is updated based on the analysis of changes in user needs using a visual effects user profile database, including the following steps:

[0026] Based on user interaction records, analyze changes in their preferences for different types of special effects;

[0027] Analyze changes in user interaction behavior over different time periods;

[0028] The evaluation mechanism analyzes the trend of demand changes over a certain period of time based on data from the user profile database. The quantitative indicators of demand changes include the rate of change of preferences, the magnitude of demand fluctuations, and the correlation of user behavior.

[0029] Based on changes in user needs, push special effects that match user preferences; dynamically adjust push content based on real-time user behavior; and optimize push frequency and timing based on changes in user activity and special effect preferences.

[0030] In a preferred embodiment, each special effects element is weighted and adjusted according to various dimensions of the special effects evaluation, as expressed by: ,in, For optimized special effects performance, For original special effects performance, Let i be the weight of the i-th evaluation indicator. Let be the score of the i-th evaluation indicator, and n be the total number of evaluation indicators.

[0031] In a preferred embodiment, the evaluation of special effects performance integration information is based on an effect evaluation model to quantify the quality of each special effects element, including the following steps:

[0032] Obtain evaluation metrics, including visual performance quality, interaction response quality, user satisfaction, and performance stability;

[0033] The evaluation metrics are input into the effect evaluation model to quantify the quality of each special effects element. The effect evaluation model expression is as follows: ,in, The final quality score for the special effects elements. Let i be the weight of the i-th evaluation indicator. Let be the score of the i-th evaluation indicator, and n be the total number of evaluation indicators. The higher the final quality score of the special effects element, the better the quality of the special effects element.

[0034] In a preferred embodiment, a special effects content integration algorithm is used to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion pointing information, including the following steps:

[0035] Extract special effects elements from various interactive scenarios, and then label and classify these special effects elements;

[0036] Before integration, all types of data need to be cleaned and standardized;

[0037] Calculate the correlation between special effects elements and user behavior data, and evaluate which special effects elements perform well under different user behaviors;

[0038] Based on the calculated correlation, each special effect element is assigned a weight, and the weight represents the importance of the special effect element in the behavioral scenario.

[0039] Integrate all weighted special effects elements and user behavior data to generate fused directional information.

[0040] In a preferred embodiment, the visual effects identifier is broken down into several visual effects interaction scenarios, and the effects of each visual effects interaction scenario and its interaction data with the user are analyzed, including the following steps:

[0041] Visual effects interaction scenarios include user triggers, effect responses, and user feedback;

[0042] Each visual effect identifier is analyzed hierarchically based on its triggering events and response effects. Each identifier contains multiple sub-scenes, which vary depending on the user's behavior.

[0043] Analyze user behavior patterns that trigger visual effects to determine which effects attract user attention.

[0044] In a preferred embodiment, obtaining the visual effect identifiers existing in the current special effects push project includes the following steps:

[0045] Visual effect identifiers are symbols, codes, or tags used in special effects push projects to uniquely identify a certain special effect or interactive element. Each identifier represents a special effect element, including visual effects and user status.

[0046] Visual effects identifiers are obtained from the project by parsing the project's configuration file or database structure, and then classified and labeled.

[0047] In a preferred embodiment, visual effects identifiers are obtained from the project by parsing the project's configuration file or database structure, including the following steps:

[0048] By retrieving the configuration files or tables in the database of the project, the stored special effects identifier information is extracted, and visual special effects identifiers related to the current push project are filtered. By analyzing the current project requirements, it is confirmed which visual special effects identifiers meet the push conditions, including filtering by type or triggering method.

[0049] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0050] This invention significantly improves the intelligence and personalized recommendation capabilities of a visual effects push system by introducing technologies such as visual effects interaction scene analysis, effects content integration algorithms, and effect evaluation models. First, by breaking down visual effects identifiers into multiple interaction scenes and combining them with user behavior data for in-depth analysis, this method can dynamically identify and understand users' effects preferences and their real-time changes. This analysis can not only accurately evaluate the quality of each effects element but also generate high-quality fusion guidance information, providing a basis for the optimization and processing of effects. Second, based on the globally optimized effects execution scene information, the method can update and build a user profile database in real time, improving the system's response speed and personalized service capabilities. Finally, by optimizing the push strategy based on the user profile analysis results, the system can better meet user needs, improve the accuracy of visual effects content push and user experience, and overcome the problems of static push strategies and low matching in existing technologies. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0052] Figure 1 This is a flowchart of the processing method of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example 1: Please refer to Figure 1 As shown in this embodiment, a visual effect processing method includes the following steps:

[0055] Step S1: Obtain the visual effects identifiers that exist in the current special effects push project;

[0056] Step S2: Decompose the visual effects identifier into several visual effects interaction scenarios, and analyze the effects of each visual effects interaction scenario and its interaction data with users;

[0057] Step S3: Use the special effects content integration algorithm to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion pointing information;

[0058] Step S4: Evaluate the integration of special effects performance with information based on the effect evaluation model, and quantify the quality of each special effects element;

[0059] Step S5: Based on the special effects performance fusion direction information and effect evaluation results, perform special effects optimization processing to generate globally optimized visual effects execution scene fusion direction information;

[0060] Step S6: Utilize the globally optimized visual effects execution scene fusion pointing information to construct the corresponding visual effects user profile library;

[0061] Step S7: Analyze changes in user needs based on the visual effects user profile database and update the push strategy for the current effects push project.

[0062] This application significantly improves the intelligence and personalized recommendation capabilities of the visual effects push system by introducing technologies such as visual effects interaction scene analysis, effects content integration algorithms, and effect evaluation models. First, by breaking down visual effects identifiers into multiple interaction scenes and combining them with user behavior data for in-depth analysis, this method can dynamically identify and understand users' effects preferences and their real-time changes. This analysis can not only accurately evaluate the quality of each effects element but also generate high-quality fusion guidance information, providing a basis for the optimization and processing of effects. Second, based on the globally optimized effects execution scene information, the method can update and build a user profile database in real time, improving the system's response speed and personalized service capabilities. Finally, by optimizing the push strategy based on the user profile analysis results, the system can better meet user needs, improve the accuracy of visual effects content push and user experience, and overcome the problems of static push strategies and low matching in existing technologies.

[0063] Step S1: Obtain the visual effects identifiers that exist in the current special effects push project.

[0064] Obtaining the visual effects identifiers present in the current visual effects push project is the first step in the entire visual effects processing workflow. Its purpose is to identify and extract relevant visual effects identifiers from the project, providing foundational data for subsequent visual effects scene analysis and optimization. This step requires a systematic analysis of the structure and characteristics of the visual effects project to ensure that the selected identifiers meet the requirements of subsequent processing.

[0065] Before acquiring visual effects identifiers, it's essential to understand that a "visual effects identifier" refers to a symbol, code, or tag used to uniquely identify a specific visual effect or interactive element within a visual effects push project. It may be a specific ID, string, image style, or metadata. Each identifier represents an independent visual effect element, which may include: visual effects (such as flashes, lights, color gradients, etc.), interactive effects (such as clicks, swipes, drags, etc.), and user states (such as selected state, hover state, etc.).

[0066] Retrieving effect identifiers from a project typically involves parsing the project's configuration file or database structure. The project's configuration file usually contains data linking effect identifiers to their specific effects; this data may be stored in a database or within the code structure. This step includes the following sub-steps:

[0067] Extract the stored visual effect identifier information by searching the project's configuration files (such as XML or JSON formats) or tables in the database. Filter the visual effect identifiers relevant to the current push project. Analyze the current project requirements to determine which visual effect identifiers meet the push criteria. For example, visual effect identifiers may be filtered by type (such as animation, effect display, user interaction, etc.) or trigger method (such as click, swipe, page load, etc.).

[0068] Because special effects projects may be updated over time or through version iterations, the management of special effects identifiers needs to support dynamic updates. Dynamic updates include:

[0069] When new special effects are requested or added to a project, the system needs to update configuration files or database tables to add the new identifiers. For outdated or no longer used effect identifiers, deletion or replacement is required within the project. Deletion operations must ensure that the identifier is no longer referenced to avoid redundant data in the system. Sometimes, the attributes of special effects (such as duration, color change, etc.) may change. In this case, the relevant information of the identifier needs to be updated to ensure consistency in effect performance.

[0070] For a large-scale visual effects push project, all visual effects tags may fall into multiple categories. To effectively manage tags, they are typically categorized and labeled, for example:

[0071] Classified by type: such as static effects, dynamic effects, interactive effects, etc.

[0072] Classified by trigger method: such as user click, page loading, mouse hover, etc.

[0073] Categorize by user status: such as user logged in, user not logged in, user status after purchasing goods, etc.

[0074] These categories facilitate quick retrieval and filtering of special effects icons. For example, the "click effects" category in a project may include multiple icons, involving multiple click events and their corresponding visual effects.

[0075] The acquired visual effects identifiers need to be stored in the system and effectively transmitted during processing. For example, the identifiers can be stored in the following structure:

[0076] For effects processed in real time, the tags can be stored in in-memory data structures (such as hash tables or dictionaries) to improve query efficiency. For historical data or long-term projects, effect tags can be stored in a database, supporting on-demand querying and analysis. When effect tags need to be transmitted across multiple modules or systems, message queues can be used for asynchronous processing to ensure timely updates. The processing flow is as follows:

[0077] Input parameters: Project configuration data (configData), which may be a JSON string or a database query result. Processing logic:

[0078] Parse configData into an operable data structure (such as a Python dictionary).

[0079] Traverse the parsed data, identify and extract all visual effect identifiers (such as effect_id).

[0080] Each extracted special effects identifier is categorized and labeled to ensure it meets the push notification requirements.

[0081] Output: Returns a list containing all effect identifiers that meet the criteria, possibly along with relevant category information.

[0082] Through the above steps and algorithm design, the system can efficiently and accurately extract all visual effect identifiers in the current special effects push project, laying a solid foundation for subsequent processing steps.

[0083] Step S2: Decompose the visual effects identifier into several visual effects interaction scenarios, and analyze the effects of each visual effects interaction scenario and its interaction data with users.

[0084] In the visual effects processing method, the second step is to break down the visual effects identifier into several visual effects interaction scenarios and analyze the effects of each scenario and its interaction data with the user. The core objective of this step is to gain a deep understanding of the interaction logic, performance, and interaction methods between the user and the effects behind each visual effect, thereby providing data support for subsequent effect optimization and push strategies.

[0085] Visual effect icons typically represent a specific visual effect or interactive action, but in practice, they do not exist in isolation. Each effect icon often corresponds to one or more interactive scenarios. The first step in breaking down effect icons is to identify these interactive scenarios, which are usually driven by different user behaviors, environments, or triggering conditions. An interactive scenario refers to a complete context experienced by a user when interacting with a visual effect. These scenarios include not only the effect itself but also the triggering and feedback of user behavior. Specifically, interactive scenarios may include:

[0086] User-triggered actions include clicking, swiping, mouse hovering, and page scrolling.

[0087] Special effects responses: such as blinking, transformation, fading, animation playback, etc.

[0088] User feedback includes: status changes triggered by visual effects, data submission, and information display.

[0089] When breaking down each effect identifier, a hierarchical analysis can be performed based on the effect's "trigger event" and "response effect." Each identifier may contain multiple sub-scenes, which vary depending on user behavior. For example, a button click effect might be divided into the following sub-scenes:

[0090] Before clicking: The button is in its normal state.

[0091] Click-triggered: When a user clicks a button, the button's color or shape changes, possibly accompanied by animation effects.

[0092] Feedback after clicking: After the button is clicked, the page content changes and new effects may appear, such as transition animations or new elements appearing.

[0093] After breaking down the interaction into interactive scenarios, the next step is to conduct a detailed analysis of the special effects for each scenario. The purpose of this step is to evaluate the quality of the visual effects, the clarity of the intended message, and the intuitiveness of the user feedback. The effect analysis for each interactive scenario includes:

[0094] By analyzing the smoothness of special effects, the fluidity of animation, and the harmony of color changes, we can assess whether the special effects meet the design expectations. For example, if the special effects are designed as fade-in / fade-out effects, but the animation is choppy or the response is delayed, it will seriously affect the user experience. The design of special effects needs to be visually attractive or impactful enough for users, but not too abrupt. The analysis should consider the expressiveness of the special effects and the user's psychological reaction. Does the special effect match the current scene? For example, when displaying a shopping cart page, adding a flashing effect to attract users' attention may help improve the conversion rate, but if the page style is simple and clean, overly dazzling special effects may interfere with the user's operating experience.

[0095] When analyzing each visual effects interaction scenario, in addition to the performance of the effects themselves, it is also necessary to examine the user interaction data with the effects. User interaction behavior provides important evidence for evaluating the effectiveness of the effects. Therefore, it is necessary to analyze user interaction data from multiple dimensions:

[0096] Analyze user behavior patterns when triggering visual effects, such as click-through rate, swipe frequency, and mouse hover time. This data can reveal which effects are more attractive to users and which effects have poor interactive response.

[0097] By analyzing the relationship between user interactions and special effects, we can assess whether the effects align with users' expected actions. For example, if a button effect is designed with a delayed loading animation, excessively long delays may cause users to become impatient or confused, leading to erroneous actions.

[0098] After obtaining user interaction and performance data, a comprehensive analysis is needed to determine the relationship between the performance of the special effects and user behavior. For example, a particular effect might trigger a large number of user clicks, but if these clicks do not lead to the expected page loading or response, it indicates a problem with the interaction design of the effect. This analysis process not only helps identify the strengths and weaknesses of the special effects but also uncovers potential areas for optimization. Further refinement and tagging of each visual effect interaction scenario facilitates subsequent analysis and optimization. For example, tags can be assigned to each interaction scenario, such as:

[0099] Interaction type tags: such as click, hover, scroll, etc.

[0100] Effect type tags: such as blinking, gradient, bouncing, etc.

[0101] User status tags: such as active, not logged in, first visit, etc.

[0102] These tags provided strong support for subsequent special effects optimization and personalized push notifications.

[0103] The processing logic of this step includes: breaking down each special effect identifier into multiple sub-scenes based on its interaction scenario; each sub-scene including user behavior, special effect performance, and response data; analyzing the visual effect performance in each interaction scenario, evaluating its quality and effectiveness, and checking whether the effect matches the scenario; collecting and analyzing user interaction data, and evaluating the relationship between the effect and user behavior in each interaction scenario; and comprehensively evaluating the effect of each visual effect interaction scenario by combining the special effect performance with user data, and identifying optimization opportunities.

[0104] In this analysis process, data analysis and user feedback played a crucial role. By refining and labeling the interaction scenarios, they provided rich information for subsequent special effects optimization and personalized push notifications.

[0105] Step S3: Use a special effects content integration algorithm to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion direction information.

[0106] In the visual effects processing workflow, the third step is to analyze each visual effects interaction scene using an effects content integration algorithm. This integrates relevant effects elements and user behaviors within the interaction scene to generate effects performance fusion guidance information. This step aims to identify and integrate highly relevant effects elements with optimization potential from multiple interaction scenes, thereby providing precise data support for effects optimization and the formulation of push strategies.

[0107] Each visual effects interaction scenario contains multiple effects elements, such as animation effects, color changes, particle effects, and interface changes. First, these effects elements need to be extracted from each interaction scenario and then labeled and categorized. These effects elements not only include visual changes but may also involve response data related to user behavior.

[0108] Visual effects elements: such as animation timing, effect type (blinking, fading, scaling, etc.), color changes (color value, transparency, gradient mode, etc.), and graphic transformations (rotation, displacement, etc.).

[0109] User behavior-related elements include the type of event that triggers the effect (click, swipe, hover, etc.), the user's state at the time of triggering (first visit, logged in, etc.), and the frequency and duration of user interaction.

[0110] The key to integration lies in understanding the relationship between special effects and user behavior. User behavior typically influences the performance of special effects directly or indirectly, and can even determine their triggering and response. To understand this relationship, data analysis algorithms are needed to correlate user behavior data with corresponding visual effects.

[0111] At this stage, the algorithm needs to establish rules between user behavior and special effects. For example, the impact of behavior on special effects can be evaluated and modeled by collecting user interaction data in specific contexts (such as whether a response is generated immediately after a click, the relationship between the length of the click and the special effect response, etc.).

[0112] Based on user behavior data, user interaction patterns can be categorized. For example, some users may click quickly, while others may hover over a particular spot for an extended period. The algorithm needs to be able to identify these behavioral patterns and generate corresponding special response strategies for each pattern.

[0113] The core task of special effects content integration algorithms is to effectively integrate relevant special effects elements and user behavior data in each visual effects interaction scene to form fused directional information. This algorithm typically includes the following key steps:

[0114] Before integration, all types of data need to be cleaned and standardized to ensure that all special effects elements and user behavior data have consistent formats and high quality, facilitating subsequent analysis. The main tasks of data preprocessing include filling in missing values, handling outliers, and standardizing numerical ranges.

[0115] The algorithm calculates the correlation between special effects elements and user behavior data. For example, the relationship between click counts and the frequency of a particular effect, or the relationship between hover time and animation display time. By calculating these correlations, the algorithm can assess which special effects elements perform more prominently under different user behaviors.

[0116] Based on the calculated relevance, each special effect element is assigned a weight. The weight represents the importance of the special effect element in a specific behavioral scenario. For example, in a certain interaction scenario, a user's rapid click may require stronger animation feedback, and the system will assign a higher weight to that animation effect, while a long hover may receive more attention for a gradient effect.

[0117] Finally, all weighted special effects elements and user behavior data will be integrated to generate a unified guiding information. This information not only includes the performance format and triggering conditions of each special effect, but also clarifies the pairing relationship between the special effects and user behavior. The unified guiding information includes the special effects elements that need to be displayed in each visual effect interaction scenario and the corresponding user behavior characteristics.

[0118] After data standardization, we need to calculate the correlation between special effects elements and user behavior. The goal of this step is to identify which special effects elements are more strongly associated with specific user behaviors, thus determining which effects are more prominent under certain user behavior patterns. Correlation can be measured using the Pearson correlation coefficient, calculated as follows:

[0119] Where X represents special effects element data (such as the response time and duration of special effects), Y represents user behavior data (such as click frequency and swipe distance), and n represents the number of samples. and For the i-th sample, the special effect element value and the user behavior value are... and This represents the mean of X and Y. The function of this formula is to assess the correlation between effects and user behavior by calculating the correlation coefficient. The closer the correlation coefficient is to 1 or -1, the stronger the relationship between the two. Once the correlation is calculated, we need to assign a weight to each effect element based on these results. The weight reflects the importance of the effect element in a specific interaction scenario. If an effect element has a strong positive correlation with user behavior (such as clicking or hovering), then the weight of this effect element will be higher. Conversely, if the correlation is weak or negative, the weight of this effect element will be lower.

[0120] This fused information will serve as the basis for subsequent decision-making and push strategies, helping the system dynamically adjust the content and presentation of special effects during real-time interactions. For example, based on user behavior during specific interactions, the system can prioritize displaying certain types of special effects or adjust their animation effects to better meet user needs.

[0121] The generated special effects rendering and blending information needs to be stored in a structured manner for easy analysis and optimization. Typically, this blending information is stored in formats such as JSON or XML, and includes the following main components:

[0122] Special effects identifier: A unique identifier for a special effects element or interactive scene.

[0123] Special effects elements: including the visual effect type, duration, color change, animation type, etc.

[0124] Triggering conditions: Describe user behavior patterns, such as the type of event that triggers the effect, the duration, and the characteristics of click or hover behavior.

[0125] Weights and priorities: Weighted priority information among various special effects elements and behaviors, which facilitates the selection of the optimal solution in subsequent processing.

[0126] The processing logic of the special effects content integration algorithm can be divided into the following stages:

[0127] Data extraction and preprocessing: Extract special effects elements and user behavior data from each visual effects interaction scene, and perform data cleaning and standardization.

[0128] Correlation Calculation and Weight Allocation: Calculate the correlation between user behavior and special effects elements, and assign weights to each element.

[0129] Integration and generation of fusion-oriented information: Based on the weighted results, special effects elements and user behavior information are integrated to form fusion-oriented information.

[0130] Structured storage and application: The information is stored in a structured format to facilitate subsequent analysis, optimization and push.

[0131] Through the above process, the special effects content integration algorithm can effectively integrate special effects elements and user behavior data in various interactive scenarios, and generate fusion-oriented information that helps optimize user experience and push strategies.

[0132] Step S4: Evaluate the integration of special effects performance with information based on the effect evaluation model, and quantify the quality of each special effects element.

[0133] In the visual effects application processing workflow, the fourth step is to evaluate the fusion of effects performance with relevant information based on an effect evaluation model, quantifying the quality of each effect element. The goal of this step is to build an effect evaluation model to quantify the quality of effects performance, helping the system identify and optimize low-quality effect elements, thereby improving the overall user experience. Through precise evaluation of each effect element, more refined effect scheduling and personalized delivery can be achieved.

[0134] To quantify the quality of special effects elements, it is first necessary to define the evaluation objectives and quality metrics. The quality of special effects is not only reflected in their visual appearance, but also includes multiple dimensions such as user interaction experience, response speed, and smoothness of effects. Common evaluation metrics include:

[0135] Visual presentation quality: including animation smoothness, color harmony, and the impact of special effects.

[0136] Interaction Response Quality: The speed and accuracy of how well the special effects respond to user actions.

[0137] User satisfaction: The attractiveness of special effects is indirectly assessed through user behavior data (such as dwell time, click rate, etc.).

[0138] Performance stability: The performance of special effects under different devices and network environments, especially the smoothness when running on low-performance devices.

[0139] Effect evaluation models are used to quantify the quality of each special effects element, typically based on a weighted average of multiple factors. The model needs to handle the performance of different special effects elements in different environments, as well as actual user feedback. To quantify the quality of special effects, a comprehensive scoring evaluation system is usually employed. The basic structure of the evaluation model can be a multi-dimensional weighted average model, whose evaluation function can be expressed as:

[0140] in, The final quality score for the special effects elements. Let i be the weight of the i-th evaluation indicator. Let be the score for the i-th evaluation indicator, and n be the total number of evaluation indicators. This formula calculates a comprehensive quality score for each effect element based on different evaluation dimensions. Evaluation indicators from different dimensions are weighted using weighting coefficients to ensure that the most important factors have a significant impact on the final score.

[0141] Each evaluation dimension needs to be refined based on the actual situation, and a corresponding score should be obtained through appropriate calculation methods. The following are methods for refining several key evaluation dimensions:

[0142] Visual presentation quality (Evisual): This involves scoring the smoothness and color harmony of animation using image processing algorithms or manual evaluation. Specifically, computer vision techniques can be used to analyze the smoothness of color changes and the naturalness of transitions in special effects elements. The expression is: ,in, The score is based on visual performance. j represents the quality score of the j-th frame of animation, and m represents the total number of frames in the animation. The smoothness of the animation is evaluated by analyzing the visual transition between each frame and the previous frame.

[0143] Interaction quality is evaluated by recording the time interval (latency) between user actions and effect responses. For example, shorter response times and higher accuracy result in higher evaluation scores. Interaction quality can be calculated using the following formula:

[0144] ,in, Rate the quality of the interactive response. Let p be the time delay between the Kth user action and the effect response. The significance of this formula is to improve interaction quality by reducing the delay time; the shorter the delay, the higher the score.

[0145] User satisfaction (E_satisfaction): User satisfaction is assessed through user behavior data analysis, such as user click-through rate (CTR) and dwell time. CTR and dwell time in re-interaction scenarios are obtained, and CTR and dwell time are normalized to map their values ​​to the range [0, 1]. The CTR and dwell time after normalization are summed to obtain the user satisfaction score.

[0146] Performance stability (E_performance): Measures the smoothness of special effects running on different devices and network environments. The performance stability score is obtained by dividing the average frame rate (FPS) by the loading time (Load-Time).

[0147] By using a quality assessment based on an effectiveness evaluation model, quantitative quality indicators can be provided for each special effects element. A multi-dimensional comprehensive scoring system can then identify poorly performing special effects elements, allowing for targeted optimization. This process not only improves user experience but also provides data support for optimizing special effects delivery strategies.

[0148] Step S5: Based on the special effects performance fusion direction information and effect evaluation results, perform special effects optimization processing to generate globally optimized visual effects execution scene fusion direction information.

[0149] In the visual effects application processing workflow, the fifth step is to optimize the visual effects based on the effect performance fusion direction information and effect evaluation results, generating globally optimized visual effects execution scene fusion direction information. The main goal of this step is to optimize the visual effects based on the effect evaluation results of the previous step, improving their effect and interactive experience, making the effects smoother, more natural, and more attractive in various scenarios. Through global optimization, the performance of the effects can achieve better overall coordination, thereby providing a more refined user experience. When optimizing effects, it is first necessary to clarify the optimization goals. Optimization is not limited to improving the visual performance of individual effect elements, but also includes improvements in the following dimensions:

[0150] Smoothness of effects: Ensure that special effects can be presented smoothly on different devices and in different environments, avoiding problems such as stuttering and delay.

[0151] Interactive responsiveness: Improve the immediate response of special effects to user interactions and reduce unnecessary delays or accidental triggering.

[0152] Visual harmony: Ensure harmony between the various visual elements of the special effects, including color matching and animation smoothness, so that they are consistent with the overall style of the application.

[0153] Personalized user experience: Dynamically adjust the performance of special effects based on user behavior and preferences to provide personalized visual feedback.

[0154] The optimization strategy is based on the results of the previous performance evaluation. The key to optimization lies in identifying low-scoring effect elements, recognizing their problems, and making targeted improvements. The optimization strategy can be implemented from the following aspects:

[0155] For special effects with performance bottlenecks, such as stuttering caused by overly complex animations, performance pressure can be reduced by simplifying the complexity of the animation, reducing the rendering burden of the special effects, or by using lazy loading.

[0156] For animation effects that are choppy or jumpy, smoother transition effects can be used, such as using Bézier curves to smooth the animation transitions and increase the smoothness of the animation.

[0157] By reducing the response latency of special effects, the matching degree between special effects and user behavior can be optimized. For example, some special effects may have a long response time, and the effect may not be displayed in time after the user clicks. The response speed can be improved by shortening the animation duration or optimizing the rendering method.

[0158] Based on users' historical behavior and preferences, special effects are personalized and optimized. For example, different visual effects are used for active users or first-time visitors to enhance user engagement.

[0159] The optimization algorithm is the core tool for improving special effects performance. Its design philosophy is to dynamically adjust the performance of special effects based on preliminary effect evaluation results, combined with the performance of the special effects and user feedback data. Each element of the special effects is weighted and adjusted according to various dimensions of the effect evaluation (such as visual performance, interaction response, user satisfaction, etc.). Elements with poor performance will receive higher adjustment weights and be optimized first. The optimization logic can be expressed as:

[0160] ,in, For optimized special effects performance, For original special effects performance, Let i be the weight of the i-th evaluation indicator. Let be the score of the i-th evaluation indicator, and n be the total number of evaluation indicators. This formula adjusts the performance of the special effect based on the evaluation results, enhancing the weaker aspects and maintaining or slightly adjusting the stronger aspects.

[0161] Gradual Optimization and Feedback Mechanism: Optimization should follow the principle of gradual optimization, meaning that each effect should be modified in small, incremental ways, rather than making drastic changes. After each adjustment, the system should provide real-time feedback to users, such as by measuring the optimization effect through data like click-through rate and dwell time. If the optimization is effective, further adjustments can be made; if the effect is unsatisfactory, the optimization should be rolled back and re-analyzed.

[0162] After optimizing individual special effects elements, a global optimization of the entire visual effects scene is needed to ensure that all optimized special effects elements are presented in a coordinated manner throughout the scene. The key to global optimization is the coordination between special effects elements, including consistency in visual style, smoothness of animation, and continuity of user experience.

[0163] When performing global optimization, the optimization results of all special effects elements must first be uniformly processed to ensure that the transitions between different special effects are natural and the responses are consistent. This process usually involves optimizing the overall weight and order of special effects elements to ensure that the user's interactive experience is not disrupted by conflicts or inconsistencies between special effects.

[0164] The optimized visual effects execution scene fusion information will include all adjusted and optimized effect elements and their relationships with each other. Each effect element will not only include its basic visual effects and triggering conditions, but also describe its coordination with other effects and the impact of changes in user behavior.

[0165] For example, multiple special effects may occur simultaneously during page loading. After optimization, it should be ensured that the loading order and animation effects of each special effect do not interfere with each other, and the response time and duration of each special effect should be appropriately adjusted according to the user's needs.

[0166] Generate globally optimized visual effects execution scene fusion pointing information.

[0167] After global optimization, the system will generate new visual effects execution scene fusion pointer information. This information will include the following:

[0168] Optimization results of special effects elements: The optimized effect of each special effect, such as the modified animation time, delay, transition effect, etc.

[0169] Global coordination strategy: The coordination relationship between special effects elements, including the interaction between elements and the timing of triggering.

[0170] User behavior data: Optimization plans adjusted based on user interaction data, such as changes in user behavior patterns and preferred effects.

[0171] The final optimized scene fusion pointing information will be provided as new input to the subsequent special effects push system to achieve a personalized visual experience. The processing logic is as follows:

[0172] Based on the results of the previous evaluation, determine which special effects elements need optimization and which elements perform well and can remain unchanged.

[0173] Based on the evaluation results, specific optimization schemes were designed, involving improvements in multiple dimensions such as visual effects, response time, and animation smoothness.

[0174] The special effects elements are improved based on weighted adjustment, step-by-step optimization, and feedback mechanisms.

[0175] The optimized special effects are coordinated as a whole to ensure that the special effects elements in the whole scene work together to achieve a good user experience.

[0176] Based on the global optimization results, the final visual effects execution scene fusion direction information is generated and provided to the subsequent push and display system.

[0177] Through this series of optimization processes, the system can achieve global optimization of visual effects, ensuring that each effect element can be presented smoothly and efficiently in different scenarios and user interactions, thereby improving the overall quality of user experience.

[0178] Step S6: Utilize the globally optimized visual effects execution scene fusion pointing information to construct the corresponding visual effects user profile library.

[0179] In the visual effects application processing workflow, the sixth step is to construct a corresponding visual effects user profile library by utilizing the globally optimized visual effects execution scene fusion information. The construction of this user profile library is the foundation of personalized push and recommendation systems. Its purpose is to build a personalized visual effects profile for each user based on user behavior data, visual effects interaction data, and optimized visual effects execution information. This user profile not only describes the user's preferences for visual effects but also provides in-depth evidence for visual effects push and optimization, thereby providing users with a customized visual experience in subsequent interactions.

[0180] User personas are multi-dimensional user description models built by analyzing user behavior, interests, preferences, and other multi-dimensional data. In visual effects applications, user personas are primarily used to describe the relationship between users and effects, specifically including:

[0181] User preferences: What types of special effects do users prefer, such as animation effects, color gradients, particle effects, etc.

[0182] User behavior: The interaction patterns between users and special effects, such as clicking, swiping, and hovering.

[0183] Special effects reactions: User feedback on special effects, such as dwell time, click-through rate, and whether to continue interacting. The goal of building user profiles is to more accurately identify user needs, so that special effects push and optimization can better meet the personalized needs of each user, thereby improving user experience and increasing user stickiness.

[0184] When building a user profile database, the first step is to map the globally optimized visual effects execution scenario integration information to the user's actual interaction data. Whenever a user interacts with a particular effect, the system needs to record the effect's relevant information and map this information to the user's behavior data. The core of this process is matching each element in the optimized visual effects execution scenario with the user's preferences and behaviors.

[0185] The elements of information that guide the integration of special effects execution scenarios include: the type of visual effect, triggering conditions, duration, and coordination with other special effects.

[0186] Elements of user behavior data include: number of clicks, click location, hover time, and user's historical preferences.

[0187] Each time a user interacts with an effect, the system records the user's behavior and pairs it with the corresponding effect information. For example, if a user frequently clicks on an effect with a flashing effect within a specific time period, the system will associate this behavior with the relevant information of that effect and update the preference value for the flashing effect in the user profile.

[0188] The storage and management of user profile data is a crucial part of the entire process. To ensure efficient data management and rapid access, user profile databases typically employ a hierarchical storage structure. This data can be stored in relational databases, non-relational databases, or graph databases, depending on the system's requirements.

[0189] Relational databases are suitable for storing structured user behavior data and special effects information, facilitating complex queries and analysis.

[0190] No relational databases: suitable for storing large-scale, distributed user data, and support high-concurrency write operations.

[0191] Graph databases offer more efficient storage and querying methods for analyzing the relationships between user behavior and special effects, especially in analyzing the correlation between user behavior patterns and special effects.

[0192] When storing data, a unique profile needs to be created for each user, including the user's effect preferences, behavior records, and interaction history. Whenever a user interacts with a new effect, the system updates that user's profile information in real time.

[0193] User profiles are dynamic models, and the information needs to be constantly updated as user behavior and preferences change. To ensure the timeliness and accuracy of user profiles, the system needs to automatically update the profile content after each user interaction with the special effects. This update can be based on the following strategies:

[0194] Incremental updates: Each time a user interacts with an effect, only the feature values ​​related to that interaction are updated. For example, if a user clicks on a new type of effect, the system will record the number of clicks on that type of effect and update the user's preference data.

[0195] Periodic Reconstruction: Regularly conduct comprehensive evaluations and reconstructions of user profiles, recalculating various characteristics based on user behavior data and preference changes over a period of time. For example, if the click frequency of a certain special effect type has increased significantly over a period of time, its weight in the user profile can be increased.

[0196] The key to dynamic updates is based on changes in users' long-term behavioral patterns rather than single interactions. Therefore, it is necessary to analyze users' long-term trends and short-term preferences when updating.

[0197] User profiles are not merely static datasets; they should encompass multiple levels of features to describe users' multidimensional needs. During construction, data mining and feature engineering are needed to extract features that significantly influence effects preferences. For example, user preferences for animation effects, color effects, and particle effects. If users prefer interactive methods like clicking, swiping, and hovering, the system can adjust the response speed and presentation of effects based on these behaviors. Based on user interaction feedback, the system can identify which effects keep users engaged longer and which cause them to quickly leave. Through feature optimization, user interests in specific types of effects can be more accurately identified, allowing for more personalized effect recommendations.

[0198] The completed user profile library for visual effects will form the foundation for personalized effect push, recommendation, and optimization. By analyzing user profiles, the system can push appropriate effects based on users' individual needs during future interactions. For example, the system can push effects related to a user's interests based on their effect preferences. For instance, if a user prefers particle effects, the system will prioritize displaying effects with particle effects. Based on user profiles, the display method, animation time, and effect type of effects can be dynamically adjusted to improve the user experience.

[0199] Furthermore, the user profile database can provide data support for subsequent special effects development, helping the development team understand user demand trends and preference changes, thereby optimizing special effects design. The processing logic is as follows:

[0200] Each time a user interacts with a special effect, the system matches the user's behavioral data with the globally optimized execution scenario information of the special effect, recording this data in the user profile. The system generates or updates personalized user profiles based on data such as the frequency and duration of user interactions with the special effects. Through data mining and feature engineering, key features such as user preferences, interaction methods, and feedback types are extracted. All user profile data is stored in a database and regularly updated and optimized. Using this constructed user profile database, the system can perform personalized special effect recommendations and optimize user experience.

[0201] Through these steps, the system can build a precise user profile library for visual effects, which not only helps to achieve personalized effects push, but also provides users with a richer and more customized visual experience.

[0202] Step S7: Analyze changes in user needs based on the visual effects user profile database and update the push strategy for the current effects push project.

[0203] In the visual effects application processing workflow, the seventh step is to analyze changes in user needs based on the visual effects user profile database and update the push strategy for the current effects push project. The core purpose of this process is to ensure that visual effects pushes can be dynamically adjusted according to changes in user needs, preferences, and behaviors, thereby achieving a more personalized and efficient user experience. As time goes by and user behavior changes, the effects push strategy needs to be continuously optimized to cope with changes in the market environment and fluctuations in user needs.

[0204] The first stage of this process requires an in-depth analysis of changes in user needs. These changes manifest in multiple ways, including but not limited to shifts in special effects preferences, changes in interaction methods, and the demand trends of different user groups. The key to this analysis lies in identifying long-term trends and short-term changes in user behavior based on dynamic data from the user profile database. This analysis is primarily conducted through the following directions:

[0205] Changes in Special Effects Preferences: Based on user interaction records, analyze changes in their preferences for different types of special effects (such as animation, particles, lighting effects, etc.). For example, a certain user group may show a strong interest in lighting effects at one time, while at another time they may prefer simple color gradient effects.

[0206] Analyze changes in user interaction behavior over different time periods, such as click-through rate, swipe frequency, and dwell time. If the interaction frequency of a certain type of effect increases significantly, it may mean that user demand for that effect is growing, and the system can adjust its push strategy based on this trend.

[0207] User needs typically exhibit certain distribution patterns, such as active users, first-time visitors, and users who have previously purchased products. The needs of different groups can vary significantly, therefore it is necessary to segment needs and develop differentiated push strategies for each group.

[0208] To accurately quantify changes in user needs, the system needs to design a mechanism for evaluating these changes. This mechanism will analyze data from the user profile database to determine trends in user needs over a specific time period. Commonly used metrics for quantifying user needs include:

[0209] Preference variability rate: Measures the rate at which user preferences for a particular effect type or element change. It is calculated by comparing user interactions and feedback on an effect over different time periods. For example, if the click-through rate of an effect increases by 20% in the past month, the preference variability rate is +20%.

[0210] Demand fluctuation range: This reflects the degree of fluctuation in user demand. A large demand fluctuation range may mean that users' demand for certain effects changes more frequently, and the system needs to adjust its push strategy more flexibly.

[0211] User behavior correlation: By analyzing the correlation between user behavior and special effects performance, the accuracy of special effects push notifications is determined. The system can use this metric to evaluate the matching degree between current special effects push notifications and user needs.

[0212] The calculation logic of these metrics can help the system assess changes in user needs in real time through time-series analysis and comparison of user interaction data.

[0213] Once changes in user needs are identified, the system needs to dynamically adjust its special effects push strategy based on these changes. Adjusting the push strategy requires considering several factors: pushing special effects that better match user preferences based on changes in user needs. For example, if a user has recently been frequently interacting with light effects, the system will prioritize pushing content with light effects while reducing the frequency of other types of effects.

[0214] Based on real-time user behavior, the system dynamically adjusts push notifications. For example, if the system detects that a user spends a significant amount of time watching a particular animation effect, it may indicate a high level of interest in that type of effect. The system can then push more of these effects and even incorporate similar effects into subsequent interactions. The system needs to optimize push frequency and timing based on changes in user activity and effect preferences. For instance, the frequency of effect pushes can be increased for active users, while for first-time users, push notifications should be less disruptive, ensuring the content is concise and clear. To ensure the effectiveness of the push strategy, the system needs to establish a real-time monitoring and feedback mechanism. After each push strategy update, the system should analyze user behavior feedback (such as click-through rate, conversion rate, and dwell time) to evaluate the actual effectiveness of the strategy. If the results are unsatisfactory, the system will adjust based on the feedback. This mechanism typically includes:

[0215] The effectiveness of push notifications can be evaluated by quantifying user interaction data. If a certain type of special effect push notification has a low conversion rate, its push frequency can be reduced.

[0216] Based on the evaluation results, the special effects push strategy will be dynamically adjusted. For example, by analyzing user feedback on different special effects, if it is found that a certain type of special effect is not attractive enough to users, the system will adjust the push content and add other special effects that are more attractive to users.

[0217] The system extracts data on changes in user needs from a user profile database, calculating metrics such as preference change rate, demand fluctuation amplitude, and behavioral relevance. Based on the demand change data and algorithm analysis results, it dynamically adjusts the content, frequency, and timing of special effects push notifications. After each strategy adjustment, user feedback is monitored in real time, and the push strategy is continuously optimized through an effectiveness evaluation mechanism. Through this process, the system can dynamically adjust its push strategy to achieve personalized and efficient special effects push notifications based on changes in user needs.

[0218] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0219] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for processing visual effects, characterized in that: The processing method includes the following steps: Step S1: Obtain the visual effects identifiers that exist in the current special effects push project; Step S2: Decompose the visual effects identifier into several visual effects interaction scenarios, and analyze the effects of each visual effects interaction scenario and its interaction data with users; Step S3: Use the special effects content integration algorithm to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion pointing information; Step S4: Evaluate the integration of special effects performance with information based on the effect evaluation model, and quantify the quality of each special effects element; Step S5: Based on the special effects performance fusion direction information and effect evaluation results, perform special effects optimization processing to generate globally optimized visual effects execution scene fusion direction information; Step S6: Utilize the globally optimized visual effects execution scene fusion pointing information to construct the corresponding visual effects user profile library; Step S7: Analyze changes in user needs based on the visual effects user profile database and update the push strategy for the current effects push project; Based on the special effects performance fusion direction information and effect evaluation results, special effects are optimized and processed to generate globally optimized visual effects execution scene fusion direction information, including the following steps: Based on the effect evaluation results, combined with the special effects performance and user feedback data, the special effects performance is dynamically adjusted, and each special effects element is weighted and adjusted according to the various dimensions of the special effects evaluation. The optimization results of all special effects elements are processed uniformly, and the optimized visual effects execution scene fusion information includes all the adjusted and optimized special effects elements and their relationships with each other; Each effect element includes visual effects, trigger condition information, and a description of its coordination with other effects and the impact of changes in user behavior; After global optimization, new visual effects execution scene fusion information is generated, including the optimization results of the effects elements, global coordination strategies, and user behavior data.

2. The visual effect processing method according to claim 1, characterized in that: Using the globally optimized visual effects execution scene fusion pointing information, a corresponding visual effects user profile library is constructed, including the following steps: User profiles are used to describe the relationship between users and special effects, including user preferences, user behavior, and special effect reactions; The optimized visual effects execution scenario is integrated and mapped with the information and the user's actual interaction data. Whenever the user interacts with a certain effect, the relevant information of the effect is recorded and matched with the user's behavior data. Each element in the optimized visual effects execution scenario is matched with the user's preferences and behaviors. The user profile database is stored in a hierarchical structure, in relational databases, non-relational databases, or graph databases; When storing data, a unique profile is created for each user, which includes the user's special effects preferences, behavior records, and interaction history.

3. The visual effect processing method according to claim 2, characterized in that: Based on the analysis of user profiles of visual effects, the push strategy for the current visual effects push project is updated, including the following steps: Based on user interaction records, analyze changes in their preferences for different types of special effects; Analyze changes in user interaction behavior over different time periods; The evaluation mechanism analyzes the trend of demand changes over a certain period of time based on data from the user profile database. The quantitative indicators of demand changes include the rate of change of preferences, the magnitude of demand fluctuations, and the correlation of user behavior. Based on changes in user needs, push special effects that match user preferences; dynamically adjust push content based on real-time user behavior; and optimize push frequency and timing based on changes in user activity and special effect preferences.

4. The visual effect processing method according to claim 3, characterized in that: Based on the various dimensions of the special effects evaluation, each special effects element is weighted and adjusted, as shown in the expression: ,in, For optimized special effects performance, For original special effects performance, Let i be the weight of the i-th evaluation indicator. Let be the score of the i-th evaluation indicator, and n be the total number of evaluation indicators.

5. The visual effect processing method according to claim 4, characterized in that: The evaluation of special effects performance is based on an effectiveness assessment model, which integrates information to quantify the quality of each special effects element. This includes the following steps: Obtain evaluation metrics, including visual performance quality, interaction response quality, user satisfaction, and performance stability; The evaluation metrics are input into the effect evaluation model to quantify the quality of each special effects element. The effect evaluation model expression is as follows: ,in, The final quality score for the special effects elements. Let i be the weight of the i-th evaluation indicator. Let be the score of the i-th evaluation indicator, and n be the total number of evaluation indicators. The higher the final quality score of the special effects element, the better the quality of the special effects element.

6. The visual effect processing method according to claim 5, characterized in that: The special effects content integration algorithm is used to analyze each visual effects interaction scene, integrate the special effects elements and user behaviors related to the visual effects interaction scene, and generate special effects performance fusion pointing information, including the following steps: Extract special effects elements from various interactive scenarios, and then label and classify these special effects elements; Before integration, all types of data need to be cleaned and standardized; Calculate the correlation between special effects elements and user behavior data, and evaluate which special effects elements perform well under different user behaviors; Based on the calculated correlation, each special effect element is assigned a weight, and the weight represents the importance of the special effect element in the behavioral scenario. Integrate all weighted special effects elements and user behavior data to generate fused directional information.

7. The visual effect processing method according to claim 6, characterized in that: The visual effects identifiers are broken down into several visual effects interaction scenarios. The effects of each visual effects interaction scenario and its interaction data with users are analyzed, including the following steps: Visual effects interaction scenarios include user triggers, effect responses, and user feedback; Each visual effect identifier is analyzed hierarchically based on its triggering events and response effects. Each identifier contains multiple sub-scenes, which vary depending on the user's behavior. Analyze user behavior patterns that trigger visual effects to determine which effects attract user attention.

8. The visual effect processing method according to claim 7, characterized in that: To obtain the visual effects identifiers present in the current special effects push project, the following steps are included: Visual effect identifiers are symbols, codes, or tags used in special effects push projects to uniquely identify a certain special effect or interactive element. Each identifier represents a special effect element, including visual effects and user status. Visual effects identifiers are obtained from the project by parsing the project's configuration file or database structure, and then classified and labeled.

9. A visual effect processing method according to claim 8, characterized in that: Retrieving visual effects identifiers from a project by parsing its configuration file or database structure includes the following steps: By retrieving the configuration files or tables in the database of the project, the stored special effects identifier information is extracted, and visual special effects identifiers related to the current push project are filtered. By analyzing the current project requirements, it is confirmed which visual special effects identifiers meet the push conditions, including filtering by type or triggering method.

Images