Configuration method, system and equipment of general game popup window and medium

Abstract

The invention discloses a universal game pop-up window configuration method, system and device and a medium, and the method specifically comprises the steps: setting a unified pop-up window protocol, and determining a data format, a calling mode and an interaction process accessed by each end according to the pop-up window protocol; a mapping relation between the game service scenes and popup window configuration parameters is established, popup window content management is carried out according to the mapping relation, and the popup window configuration parameters comprise popup window style parameters and content editing rules; forming a pop-up window trigger rule set according to the pop-up window trigger condition of each game service scene, the target crowd and the arrival opportunity, and judging whether a window needs to be popped up and the priority of pop-up window information to be popped up in real time through a rule matching algorithm based on the pop-up window trigger rule set; and dynamically controlling the pop-up window triggering frequency of each user by mining the association between the user behavior mode and the pop-up window effect influence factor. According to the method, the universality, the flexibility and the individuation of the game popup window are realized.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a configuration method, system, device and medium for a general game pop-up window. Background Art

[0002] In the current gaming industry, user activity and payment conversion rate are key indicators for measuring the success of game operations. In order to improve these two indicators, game operators are constantly exploring various operating methods. Among them, in-game pop-ups are widely used in all aspects of game operations as a direct and efficient way to reach users. Pop-ups can not only deliver important information to users in a timely manner, such as event notifications, reward collection, version updates, etc., but also effectively guide users to pay and increase the overall revenue of the game.

[0003] However, with the continuous development of the game industry, the user groups are becoming increasingly diversified, and the operating environment has become more complex and changeable. At the same time, different game nodes (such as novice guidance, daily activities, festival celebrations, etc.) have different requirements for pop-up windows. This has led to the gradual exposure of many problems in the traditional pop-up window design method, such as single pop-up window content, rigid trigger mechanism, poor user experience, etc., which makes it difficult to meet user needs in different scenarios.

[0004] Specifically, traditional pop-up window design methods often use fixed templates and trigger conditions, lacking flexibility and personalization. This design method is not only difficult to attract users' attention, but may also cause users to feel bored, thereby reducing user activity and payment conversion rates. In addition, due to differences in the operating goals and user behavior characteristics of different game nodes, traditional pop-up window design methods often cannot accurately grasp the timing and frequency of pop-up window display, thus affecting the conversion effect of pop-up windows. Summary of the invention

[0005] The purpose of the present invention is to provide a configuration method, system, device and medium for a universal game pop-up window. By setting a unified pop-up window protocol, establishing a mapping relationship between game business scenarios and pop-up window configuration parameters, formulating a pop-up window triggering rule set, and dynamically controlling the user pop-up window triggering frequency and other technical means, the universality, flexibility and personalization of game pop-up windows are achieved to solve at least one of the above-mentioned prior art problems.

[0006] In a first aspect, the present invention provides a method for configuring a general game pop-up window, the method specifically comprising:

[0007] Set a unified pop-up window protocol, and determine the data format, calling method and interaction process of each terminal access according to the pop-up window protocol;

[0008] Establishing a mapping relationship between multiple game business scenarios and pop-up window configuration parameters, and managing pop-up window content according to the mapping relationship, wherein the pop-up window configuration parameters include pop-up window style parameters and content editing rules;

[0009] A pop-up window triggering rule set is formed according to the pop-up window triggering conditions, target groups and contact timing of each game business scenario. Based on the pop-up window triggering rule set, a rule matching algorithm is used to determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up;

[0010] By exploring the correlation between user behavior patterns and factors affecting pop-up effects, the pop-up triggering frequency of each user can be dynamically controlled.

[0011] In a second aspect, the present invention provides a general game pop-up window configuration system, the system specifically comprising:

[0012] The first configuration module is used to set a unified pop-up window protocol, and determine the data format, calling method and interaction process of each terminal access according to the pop-up window protocol;

[0013] A second configuration module is used to establish a mapping relationship between multiple game business scenarios and pop-up window configuration parameters, and manage pop-up window content according to the mapping relationship. The pop-up window configuration parameters include pop-up window style parameters and content editing rules;

[0014] The third configuration module is used to form a pop-up window triggering rule set according to the pop-up window triggering conditions, target groups and contact opportunities of each game business scenario, and based on the pop-up window triggering rule set, determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up through a rule matching algorithm;

[0015] The fourth configuration module is used to dynamically control the pop-up window triggering frequency of each user by mining the correlation between user behavior patterns and factors affecting pop-up window effects.

[0016] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor and a computer program stored in the memory, and when the computer program is executed on the processor, a configuration method for a general game pop-up window as described in any one of the above methods is implemented.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for configuring a general game pop-up window as described in any one of the above methods is implemented.

[0018] Compared with the prior art, the present invention has at least one of the following technical effects:

[0019] 1. The present invention realizes the versatility, flexibility and personalization of game pop-up windows by setting a unified pop-up window protocol, establishing a mapping relationship between game business scenarios and pop-up window configuration parameters, formulating a pop-up window triggering rule set, and dynamically controlling the user pop-up window triggering frequency.

[0020] 2. The present invention can accurately grasp the display timing and frequency of pop-up windows according to different game nodes and user needs, thereby improving the conversion effect of pop-up windows.

[0021] 3. The present invention continuously optimizes the pop-up strategy and improves the user experience by mining the relationship between user behavior patterns and factors affecting pop-up effects, thereby achieving a dual increase in user activity and payment conversion rate.

[0022] 4. The present invention ensures that pop-up windows can present good display effects and user experience under different operating systems and device models through platform compatibility testing and optimization, thereby improving cross-platform compatibility.

[0023] 5. The present invention sets a unified pop-up window protocol to ensure that the data format, calling method and interaction process accessed by each end (such as PC, mobile device, etc.) are consistent, thereby simplifying the complexity of development and maintenance.

[0024] 6. The present invention uses the K-means clustering algorithm to perform cluster analysis on new game business scenarios, quickly find the configuration parameters most similar to existing scenarios, and reduce the cost and time of new scenario configuration.

[0025] 7. The present invention is based on a pop-up window triggering rule set and a rule matching algorithm to determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up, thereby improving the accuracy and effectiveness of the pop-up window.

[0026] 8. The present invention analyzes the relationship between user feedback and pop-up window triggering rules through an association rule mining algorithm, and continuously optimizes the rule decision tree model to make the pop-up window triggering more in line with user expectations.

[0027] 9. The present invention mines the association between user historical behavior data and pop-up window historical display data, and establishes a mapping relationship between user behavior patterns and pop-up window effects.

[0028] 10. By setting a time window and judging whether the indicator data exceeds a preset threshold range, the present invention can timely detect abnormal pop-up windows and take corresponding processing measures, thereby ensuring the stability and reliability of the pop-up window system. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 It is a flowchart of a method for configuring a general game pop-up window provided by an embodiment of the present invention;

[0031] Figure 2 It is a structural diagram of a general game pop-up window configuration system provided by an embodiment of the present invention;

[0032] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0034] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0035] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0036] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0037] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0038] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0039] In the embodiment of the present application, the execution subject of the process includes a terminal device, which includes but is not limited to: a server, a computer, a smart phone, a tablet computer, and other devices capable of executing the method disclosed in the present application. Figure 1 A flow chart of a method for configuring a general game pop-up window disclosed in an embodiment of the present invention is shown, and the details are as follows:

[0040] S101, setting a unified pop-up window protocol, and determining the data format, calling method and interaction process of each terminal access according to the pop-up window protocol.

[0041] In this embodiment, a standard pop-up window type enumeration is first defined, such as information prompt pop-up window, confirmation pop-up window, input pop-up window, etc. Each pop-up window type contains fixed fields, such as title, content, button, etc. JSON format is used as the data format for each terminal access, and the JSON object contains fields such as pop-up window type, title, content, button text, button click event, etc.

[0042] Provide a unified pop-up window calling interface. Each end triggers the pop-up window by calling the interface and passing in the corresponding JSON data. The interface supports synchronous and asynchronous calling methods to meet the needs of different scenarios. When a user triggers an event that requires a pop-up window, the front end calls the pop-up window interface and passes in the corresponding data. After the back end receives the data, it generates a corresponding pop-up window page based on the pop-up window type and data content. The pop-up window page is displayed to the user, and the user interacts (such as clicking a button). The back end performs corresponding processing based on the user's interaction results and returns the processing results to the front end. For different terminals (such as Web, iOS, Android, etc.), the pop-up window page is adapted and optimized to ensure that the pop-up window style and interaction effect are consistent on different terminals.

[0043] In this embodiment, by defining a unified pop-up window protocol and data format, each terminal can share a set of pop-up window codes and logic. This reduces the workload of repeated development and maintenance and improves development efficiency. The unified pop-up window style and interaction process help improve the consistency of user experience. Cross-terminal adaptation ensures that the pop-up window style and interaction effect are consistent on different terminals, further improving the user experience.

[0044] In some embodiments, in the above step S101, determining the data format, calling method and interaction process of each terminal access according to the pop-up window protocol specifically includes:

[0045] According to the pop-up window protocol, combined with the platform characteristics and technical conditions of each terminal, design a preliminary implementation plan for the pop-up window function;

[0046] Conduct platform compatibility testing on the preliminary implementation plan of the pop-up window function to obtain display effects and user experience under different operating systems and device models, and obtain compatibility test results;

[0047] Analyze the compatibility test results using a decision tree algorithm to find out the key factors affecting cross-platform compatibility and obtain test analysis results;

[0048] According to the test analysis results, the preliminary implementation plan of the pop-up window function is optimized to determine the data format, calling method and interaction process of each terminal access.

[0049] In this embodiment, according to the pop-up window protocol and the characteristics of each terminal platform, the pop-up window interface layout, interaction mode and data transmission format are designed to form a preliminary implementation plan for the pop-up window function. An automated testing tool is used to perform compatibility tests on different operating systems and device models to obtain performance indicator data such as the display effect, response speed and memory usage of the pop-up window. Through user experience questionnaire surveys and behavior log analysis, user experience data such as satisfaction scores, operation completion rates and stay time for the pop-up window function are obtained. The compatibility test data and user experience data are cleaned and feature engineered to extract key feature variables that affect cross-platform compatibility. A cross-platform compatibility prediction model is established using a decision tree algorithm, and the compatibility level of the pop-up window function on the target platform is determined by the value combination of key feature variables. According to the analysis results of the compatibility prediction model, the pop-up window interface layout, interaction mode and data transmission format are optimized to improve cross-platform compatibility. Determine the access method of the pop-up window function at each end, including the called API interface, data format, interaction process and error handling mechanism, to form the final implementation plan of the pop-up window function.

[0050] For example, according to the requirements of the pop-up window protocol, combined with the characteristics and technical conditions of each terminal platform, a preliminary implementation scheme of the pop-up window function was designed. The scheme adopts HTML5 and CSS3 technology, uses media query and responsive layout to achieve cross-platform adaptive display, and uses JavaScript to achieve the interactive effects of pop-up windows, including pop-up, close, drag and drop functions. In order to test the compatibility of the scheme, mainstream operating systems such as Android, iOS, and Windows, as well as devices of different sizes and resolutions were selected for testing, and user feedback and experience scores were collected to form a compatibility test result data set. The data set was analyzed using the decision tree algorithm, and a decision tree model was constructed by calculating the information gain ratio and the Gini index to identify the key factors affecting cross-platform compatibility, mainly including screen size, resolution, browser kernel, etc. According to the test analysis results, the pop-up window scheme was optimized, using rem as the size unit, setting the minimum width and maximum width, and ensuring the display effect under different screens; the data format of each terminal was unified to JSON, providing a unified API interface, simplifying the calling method; optimizing the interactive process of the pop-up window, adding gesture operation and keyboard support, and improving the user experience.

[0051] S102, establishing a mapping relationship between a plurality of game business scenarios and pop-up window configuration parameters, and managing pop-up window content according to the mapping relationship, wherein the pop-up window configuration parameters include pop-up window style parameters and content editing rules.

[0052] In this embodiment, first, the various business scenarios in the game are clarified, such as novice guidance, task prompts, reward collection, recharge prompts, etc. For each business scenario, its characteristics and requirements are analyzed to determine the required pop-up window type and function.

[0053] Among them, pop-up style parameters: including visual style parameters such as pop-up size, shape, color, background, border, shadow, and interactive style parameters such as animation effects, pop-up position, and dwell time; content editing rules: define the layout rules of elements such as text, pictures, buttons, etc. in the pop-up, as well as the content update and review process.

[0054] According to the characteristics and requirements of the game business scenario, select appropriate pop-up style parameters and content editing rules for each scenario. Create a mapping relationship table to associate each business scenario with the corresponding pop-up configuration parameters.

[0055] According to the configuration parameters in the mapping table, write the content of the pop-up window, including elements such as text, pictures, and buttons. Establish a content review mechanism to ensure the accuracy and compliance of the pop-up window content. Dynamically update the content of the pop-up window according to the needs of game operations, such as event information, recharge discounts, etc. Through the background management system, update the configuration parameters in the mapping table in real time to achieve dynamic update of the pop-up window content. In the game code, trigger the corresponding pop-up window according to the business scenario. Dynamically load and display the pop-up window content according to the configuration parameters in the mapping table.

[0056] In this embodiment, by selecting appropriate pop-up window styles and content for each business scenario, the pop-up window is made more in line with the user's expectations and needs. Unified pop-up window content management enables the game operation team to manage and update the pop-up window content more efficiently. Through the background management system, the pop-up window content can be updated and monitored in real time, improving operational efficiency and accuracy.

[0057] In some embodiments, in the above step S102, the mapping relationship between multiple game business scenarios and pop-up window configuration parameters is established, and the pop-up window content management is performed according to the mapping relationship, specifically including:

[0058] Determine corresponding pop-up window configuration parameters according to characteristic attributes of different game business scenarios, summarize characteristic attributes of each game business scenario and its corresponding pop-up window configuration parameters, and form a pop-up window configuration database;

[0059] Obtain new game business scenarios, use K-means clustering algorithm to perform cluster analysis on the new game business scenarios and existing game business scenarios, and determine the existing game business scenarios that are most similar to the new game business scenarios;

[0060] Based on the existing game service scenario that is most similar to the new game service scenario, a pop-up window configuration parameter corresponding to the new game service scenario is acquired from the pop-up window configuration database.

[0061] In this embodiment, characteristic attribute data of game business scenarios are obtained, and the data is converted into a format suitable for cluster analysis through data preprocessing; the characteristic attribute data of existing game business scenarios are clustered using the K-means clustering algorithm to obtain game business scenarios of different categories; for each category of game business scenarios, the association rules between its characteristic attributes and pop-up configuration parameters are analyzed, and an association rule database is constructed; when there is a new game business scenario, its characteristic attribute data is extracted, and converted into a format suitable for cluster analysis through data preprocessing; the characteristic attribute data of the new scenario is input into the K-means clustering model to determine the category of the game business scenario to which it belongs; according to the category to which the new scenario belongs, the corresponding pop-up configuration parameters are obtained from the association rule database, and the parameters are applied to the pop-up configuration of the new scenario; the characteristic attribute data and user feedback data of new scenarios are continuously collected, and the clustering model and the association rule database are regularly updated to optimize the recommendation effect of the pop-up configuration parameters.

[0062] For example, by analyzing 100 different game business scenarios, the key characteristic attributes that affect the pop-up design are extracted, including game type, screen style, player group, etc., totaling 20 characteristic dimensions. For each characteristic dimension, the corresponding pop-up configuration parameters are designed, such as pop-up size, position, animation effect, etc., forming a pop-up configuration database containing 2000 data. When a new game business scenario appears, its characteristic attributes are first extracted, and then the K-means clustering algorithm is used to calculate the similarity between it and the existing scenarios in the database. By calculating the Euclidean distance between the new scenario and each cluster center, the cluster with the closest distance is found, which is the most similar game scenario. Assuming that the new scenario is closest to the second cluster center, it is considered that the new scenario is most similar to the second category of game scenarios. Then, the pop-up configuration parameters corresponding to the second category of scenarios are queried from the database, such as the pop-up width is 60% of the screen width, the height is 40%, the pop-up animation is a gradient effect, the duration is 5 seconds, etc., which are applied to the pop-up design of the new scenario, thereby realizing the automatic matching and generation of the pop-up configuration.

[0063] S103, forming a pop-up window triggering rule set according to the pop-up window triggering conditions, target groups and contact timing of each game business scenario, and based on the pop-up window triggering rule set, determining in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up through a rule matching algorithm.

[0064] In this embodiment, the pop-up window triggering conditions are first set, such as: a novice guidance pop-up window: triggered when the player first enters the game or first arrives at a certain game area; a task reminder pop-up window: triggered when the player completes or fails to complete a task; a reward collection pop-up window: triggered when the player obtains a reward but does not collect it; a recharge reminder pop-up window: triggered when the player's balance is insufficient or reaches a specific recharge amount; an event promotion pop-up window: triggered when a specific event in the game starts or when the countdown ends.

[0065] Filter out player groups that meet specific conditions based on player level, VIP level, historical consumption records, etc. For example, a new player guide pop-up window is mainly for new players, while a recharge reminder pop-up window may be targeted at players with a lower VIP level but a high consumption history.

[0066] Determine the best time to display pop-ups during the game flow to avoid interrupting players’ normal gameplay. For example, a task reminder pop-up can pop up immediately after the player completes the task, while an event promotion pop-up can pop up during the player’s free time or at the end of the game.

[0067] The above trigger conditions, target groups and contact timing are integrated into a pop-up trigger rule set. Each rule in the rule set contains the trigger conditions, target group description and contact timing description.

[0068] Collect players' game behavior data in real time, such as level changes, task completion, recharge records, etc. At the same time, record players' online status, game time, and other data for determining the timing of contact. Traverse the pop-up window trigger rule set and match the player data collected in real time with the trigger conditions, target population, and contact timing of each rule. When all conditions of a rule are met, the rule is considered to be matched successfully. Set a priority for each rule, which can be determined based on factors such as business importance and the urgency of the pop-up window. When multiple rules are matched successfully, select the pop-up window corresponding to the rule with the highest priority for display. According to the results of the rule matching algorithm, display the corresponding pop-up window information to the player. The pop-up window information includes pop-up window content, style, buttons, etc., which can be dynamically adjusted according to the configuration in the rule set.

[0069] In this embodiment, through a precise rule matching algorithm, it is ensured that the pop-up window is displayed to the right player at the right time to avoid disturbing the player's normal game. The dynamic adjustment of the pop-up window content makes the pop-up window more in line with the player's expectations and needs, improving the user experience. The rule matching algorithm can determine the pop-up demand and priority of the pop-up window in real time, allowing the game operation team to manage the pop-up window content more efficiently.

[0070] In some embodiments, in the above step S103, the step of determining in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up based on the pop-up window triggering rule set by using a rule matching algorithm specifically includes:

[0071] Convert the pop-up window triggering rule set into a decision tree, use each pop-up window triggering rule condition as a node of the decision tree, use the ID3 algorithm to train and optimize the decision tree, and generate a rule decision tree model;

[0072] Acquire user behavior data and game status data in real time, match the user behavior data and the game status data with the rule decision tree model, and obtain the pop-up priority of the pop-up information;

[0073] Based on the pop-up priority, push appropriate pop-up information to the target user, and obtain the target user's feedback data on the pop-up information that has been displayed, the feedback data including the number of clicks, the number of closes and the length of stay;

[0074] Associating the feedback data with the corresponding pop-up window triggering rules, and analyzing them using an association rule mining algorithm to obtain an association pattern between the pop-up window triggering rules and user feedback;

[0075] The rule decision tree model is optimized and adjusted according to the association rules.

[0076] In this embodiment, according to the pop-up window triggering rule set, an initial decision tree model is constructed, and each rule condition is used as a node of the decision tree. The ID3 algorithm is used to optimize the initial decision tree model, and the optimal partition attribute is selected by calculating the information gain of each node to generate an optimized rule decision tree model. The user behavior data and game status data are obtained in real time, and the data is preprocessed and feature extracted. The extracted user behavior features and game status features are input into the rule decision tree model, the nodes of the decision tree are traversed, and branch judgments are made according to the feature attributes. At the leaf nodes of the decision tree, the corresponding pop-up window information and pop-up priority are obtained, and the pop-up order of the pop-up window is determined according to the priority sorting. If the user behavior or game status changes, the latest feature data is re-acquired, and the decision tree model is input again to dynamically adjust the pop-up strategy of the pop-up window. Continuously monitor the user's feedback and interaction with the pop-up window, collect relevant data, and use it to further optimize the decision tree model to improve the accuracy of the pop-up window strategy and user experience.

[0077] According to the priority of different pop-up information output, the pop-up information with higher priority is pushed to the target user. The feedback data of the target user on the pop-up information that has been displayed is obtained, including the number of clicks, the number of closes and the length of stay, and the feedback data is stored in the database. The feedback data is cleaned, converted and integrated by using data preprocessing technology to obtain a standardized feedback data set. The standardized feedback data is associated with the corresponding pop-up trigger rules to construct a pop-up trigger rule-user feedback data association matrix. The Apriori association rule mining algorithm is used to mine frequent item sets and generate association rules on the association matrix to obtain the association pattern between the pop-up trigger rules and user feedback. According to the mined association pattern, the preset rule decision tree model is optimized and adjusted. If the user feedback corresponding to the trigger rule with a higher correlation is poor, the weight of the rule in the decision tree is reduced; if the user feedback corresponding to the trigger rule with a higher correlation is good, the weight of the rule in the decision tree is increased. The optimized and adjusted rule decision tree model is reapplied to the pop-up push system, and the priority of different pop-up information is determined according to the new decision tree model to achieve dynamic optimization of pop-up push.

[0078] For example, in actual application, the pop-up window triggering rules in 1000 game scenes are first extracted. For example, in RPG games, when the player level reaches level 10, the level gift package pop-up window is triggered; in SLG games, when the player's resource inventory is less than 1000, the resource replenishment pop-up window is triggered. Then these rules are converted into nodes of the decision tree, and each node represents a trigger condition, such as "player level ≥ 10". The decision tree is trained using the ID3 algorithm. By calculating the information gain of each node, the node with the largest information gain is selected as the decision node, and the subtree is recursively constructed to finally generate a rule decision tree model. During the game operation, player behavior data (such as login time, online time, level progress, etc.) and game status data (such as resource inventory, equipment attributes, achievement points, etc.) are collected in real time, and input into the decision tree model for classification to obtain the triggering priority of different pop-ups, such as the priority of the level gift package pop-up window is 8, and the priority of the resource replenishment pop-up window is 6. According to the priority sorting, the pop-up window with the highest priority is pushed to the player, and the player's feedback data, including the number of clicks, the number of closes, and the length of stay, is recorded. Assume that within a week, the average click rate of the level gift package pop-up window is 5%, and the average stay time is 10 seconds; the average click rate of the resource supply pop-up window is 8%, and the average stay time is 20 seconds. Using the Apriori association rule mining algorithm, with the minimum support of 05 and the minimum confidence of 8 as the threshold, it is found that the confidence of the association rule "Player level ≥ 10 → click on the level gift package pop-up window" is 6, and the confidence of the association rule "Player resource stock < 1000 → click on the resource supply pop-up window" is 9. Based on this, the node thresholds and priorities in the rule decision tree are adjusted, such as adjusting the threshold of the "Player level ≥ 10" node to "Player level ≥ 12" and the priority to 7; adjusting the threshold of the "Player resource stock < 1000" node to "Player resource stock < 800" and the priority to 85. The decision tree model is continuously iterated and optimized so that it can dynamically adjust the pop-up push strategy according to the real-time feedback of players, and improve the click-through conversion rate and user experience of the pop-up window.

[0079] S104, dynamically controlling the pop-up window triggering frequency of each user by mining the correlation between the user behavior pattern and the factors affecting the pop-up window effect.

[0080] In this embodiment, the user's browsing logs, recharge records, click behavior and other data are collected through the user behavior pattern mining system deployed on the server side. These data are preprocessed, the main access behaviors are extracted, and a user behavior pattern diagram is constructed. The user behavior pattern is deeply analyzed using machine learning algorithms, such as cluster analysis and association rule mining. The behavioral characteristics of different user groups and the association between these characteristics and pop-up effects (such as click-through rate and conversion rate) are identified. According to the model analysis results, personalized pop-up strategies are formulated for different user groups. The user's latest behavior data is tracked in real time, and the pop-up strategy is dynamically adjusted according to data changes. The effects of different pop-up strategies are evaluated through methods such as A / B testing.

[0081] In this embodiment, the personalized pop-up window strategy avoids excessive interruption of users and improves the user experience. Users no longer feel irritated and dissatisfied due to frequent pop-ups, thereby improving their satisfaction and loyalty to the platform.

[0082] In some embodiments, in the above step S104, the dynamic control of the pop-up window triggering frequency of each user by mining the association between the user behavior pattern and the factors affecting the pop-up window effect specifically includes:

[0083] Obtain user historical behavior data and pop-up window historical display data, wherein the user historical behavior data includes user attributes, browsing tracks and interactive behaviors, and the pop-up window historical display data includes pop-up window attributes, display timing, display frequency and click conversion;

[0084] After extracting feature vectors from the user historical behavior data and the pop-up window historical display data and merging the feature vectors, an Apriori algorithm is used to perform association rule mining to obtain an association rule set between user behavior unfamiliarity and pop-up window effects;

[0085] Based on the association rule set, a logistic regression model is used to establish a mapping relationship between user behavior patterns and pop-up window effects, and a binary classification model is trained. The binary classification model is used to predict the acceptance degree and conversion probability of the pop-up windows by different users in different scenarios;

[0086] Based on the binary classification model, the optimal triggering timing and frequency of the pop-up window for each user in any scenario are determined.

[0087] In this embodiment, user historical behavior data, including user attributes, browsing trajectories and interactive behaviors, and pop-up window historical display data, including pop-up window attributes, display timing, display frequency and click-through conversion, are obtained. Feature vectors are extracted from user historical behavior data and pop-up window historical display data to obtain numerical vectors representing features of different dimensions. The extracted user behavior feature vectors and pop-up window display feature vectors are merged to form a unified high-dimensional feature space. The Apriori association rule mining algorithm is used to discover the association rules between user behavior patterns and pop-up window effects in the merged high-dimensional feature space.

[0088] According to the association rule set, the feature vector of the logistic regression model is constructed, and the user behavior pattern is used as input and the pop-up window effect is used as output to train the logistic regression binary classification model. For the real-time behavior data of new users, the behavior pattern features matching the association rule set are extracted and input into the logistic regression binary classification model to predict the user's acceptance and conversion probability of the pop-up window in the current scenario. If the acceptance and conversion probability exceed the preset threshold, the pop-up window is triggered; otherwise, the user behavior is continuously monitored until the triggering condition is met. After the pop-up window is triggered, the user's feedback data on the pop-up window is obtained to update the association rule set and the logistic regression model to achieve dynamic optimization of the pop-up window strategy. Through AB testing and other methods, the effects of pop-ups at different times and frequencies are compared, the judgment threshold of the optimal triggering time and frequency is determined, and applied to the logistic regression binary classification model. Continuously track user behavior and pop-up window effect data, regularly retrain the logistic regression binary classification model, and dynamically adjust the association rules, optimal triggering time and frequency to adapt to changes in user behavior patterns.

[0089] Exemplarily, in actual applications, first obtain user historical behavior data and pop-up window historical display data. Among them, user historical behavior data includes user attributes such as age, gender, region, and user browsing trajectory (such as visited page URL, length of stay) and interactive behavior (such as likes, collections, comments, etc.) in the APP; pop-up window historical display data includes pop-up window type (such as activity notification, new function guide), display timing (such as within 5 seconds after the user opens the APP), display frequency (such as up to 3 times a day) and click conversion (such as click-through rate, conversion rate). Then, these data are extracted from feature vectors, such as converting user attributes into one-hot encoding, converting browsing trajectories into TF-IDF vectors, and converting interactive behaviors into statistical features (such as the number of likes, collection rate); pop-up window attributes, display timing and frequency are also converted into corresponding numerical features. Then, the user feature vector and the pop-up window feature vector are merged to form a complete training sample. Then, the Apriori algorithm is used to mine association rules for the training samples. Assuming that the minimum support is set to 1% and the minimum confidence is set to 60%, the association rules mined include: "Post-90s male users &&19:00-21:00 display → click-through rate ≥ 5%" (support 2%, confidence 75%), "More than 3 collection behaviors within 30 days && new function guide pop-up window → conversion rate ≥ 15%" (support 08%, confidence 65%), etc. Using these association rules, a logistic regression model is used to establish a mapping relationship between user behavior patterns and pop-up window effects. The association rules are used as features, and the click-through rate or conversion rate higher than a certain threshold (such as 5%) is used as a positive sample to train a binary classification model. After the model training is completed, the acceptance and conversion probability of different pop-ups for any user in any scenario can be predicted. Finally, based on the prediction results, the optimal triggering time and frequency of pop-ups for each user in different scenarios are determined. For example, for the combination of "post-90s male users &&19:00-21:00 display" with a high predicted click-through rate (such as ≥8%), the pop-up window triggering time can be set to 19:30 and the frequency can be set to once every 2 days; for the combination of "more than 3 collections within 30 days && new function guidance pop-ups" with a high predicted conversion rate (such as ≥20%), the pop-up window triggering time can be set to after the user's 4th collection behavior occurs, and the frequency can be set to once a week. In this way, the pop-up window push strategy can be dynamically adjusted according to the behavior patterns of different users to improve the click-through conversion effect of the pop-up window.

[0090] Furthermore, the method further comprises:

[0091] Build a user profile according to the user's historical behavior data, and design multiple sets of pop-up window strategy solutions based on the user profile;

[0092] Through the A / B testing method, conduct comparative experiments on different groups of pop-up strategy solutions to obtain feedback data on the strategy effects;

[0093] According to the feedback data of the strategy effect, a reinforcement learning algorithm is used to optimize and adjust the binary classification model.

[0094] In this embodiment, a user portrait model is constructed based on user behavior data, and users are grouped and labeled through algorithms such as clustering and association rule mining to form different user portraits. For different user portraits, multiple groups of pop-up window strategy solutions are designed, including the content, style, trigger conditions, etc. of the pop-up window, to form a candidate strategy set. The A / B test method is adopted to randomly divide users into multiple experimental groups, and each group applies different pop-up window strategy solutions to collect user feedback data, including indicators such as click-through rate and conversion rate. The result data of the A / B test is statistically analyzed to evaluate the effects of different pop-up window strategy solutions, and the strategy with the best effect is selected as the basic strategy. The strategy effect data is used as the reward signal of the reinforcement learning algorithm, and the selection strategy of the pop-up window strategy is continuously optimized through algorithms such as Q-learning to improve the benefits of the strategy. The optimized strategy is applied to the binary classification model, and it is determined whether to push the pop-up window to the user based on user characteristics and behavior data, and the model parameters are continuously adjusted according to the results of reinforcement learning to improve the accuracy of the push.

[0095] Exemplarily, first, a user profile is constructed based on the user's historical behavior data, including the user's demographic characteristics (such as age, gender, region), behavioral characteristics (such as visit frequency, length of stay, interactive behavior) and preference characteristics (such as browsing categories, purchasing brands), etc. The K-means clustering algorithm is used to divide users into multiple groups, and the user characteristics in each group are highly similar. Then, the A / B test method is used to randomly divide each user group into an experimental group and a control group. The experimental group adopts a new pop-up window strategy scheme, and the control group adopts the original pop-up window strategy. After observing for a period of time (such as 1 week), the click-through rate, conversion rate and other indicators of the two groups of users are compared to evaluate the effect of different pop-up window strategies. Finally, the strategy effect feedback data obtained by the A / B test is used as an environmental reward, and a reinforcement learning algorithm (such as the DQN algorithm) is used to optimize the binary classification model. The user characteristics and pop-up window strategy combination are used as the state space, the click-through rate or conversion rate is used as the reward value, and the state-action value function is learned through the Q-learning algorithm to obtain the optimal pop-up window strategy to be adopted in various states. By continuously iterating and optimizing the model, we eventually obtain a dynamically adjusted pop-up strategy model, which can predict the optimal pop-up strategy based on the user's real-time status and improve the overall click-through conversion effect of the pop-up.

[0096] In some embodiments, the method further comprises:

[0097] Obtain historical time series data for each pop-up window, and establish multi-dimensional indicator data for each pop-up window type using a moving average method based on the historical time series data;

[0098] By setting the time window size, determine a number of time windows;

[0099] By judging in real time whether the indicator data of the pop-up window type corresponding to any pop-up window in the current time window exceeds the preset threshold range, it is determined whether the pop-up window is an abnormal pop-up window.

[0100] In this embodiment, the historical time series data of each pop-up window type is obtained, and the moving average method is used for each pop-up window type to calculate the indicator data of multiple dimensions. Set the appropriate time window size according to business needs, and divide the historical data into several time windows. For the current time window, obtain the multi-dimensional indicator data of each pop-up window type. For each indicator, determine whether it exceeds the preset normal threshold range. If any indicator of any pop-up window type exceeds the threshold range in the current time window, the pop-up is determined to be an abnormal pop-up. A machine learning algorithm such as a support vector machine is used to train an abnormal pop-up detection model based on the indicator data of each pop-up window type in the historical time window. The pop-up window indicator data in the current time window is input into the trained model to automatically identify abnormal pop-ups and improve detection efficiency.

[0101] Exemplarily, first, the system will obtain the historical time series data of each pop-up window, such as the number of pop-up windows per day in the last month, the length of pop-up windows and other dimensions. Then, the moving average method is used to process these data, and the average value of each pop-up window type in different dimensions is calculated as the multi-dimensional indicator data of this type of pop-up window. Next, the system will set the size of the time window, such as dividing the data of the last month into 30 time windows, each window corresponding to one day's data. During real-time monitoring, the system will determine whether the various indicator data of each pop-up window type in the current time window exceeds the preset threshold range. For example, if the average number of pop-ups of a certain type of pop-up window exceeds 10 times, or the average pop-up duration exceeds 5 seconds, the pop-up window will be marked as an abnormal pop-up window. These thresholds can be set according to historical data and business needs. For example, the distribution of each indicator under normal circumstances is obtained through statistical analysis, and data beyond the normal range is defined as abnormal. In this way, the system can detect abnormal pop-ups in real time and take corresponding processing measures in time, such as suspending the push of the pop-up window, or adjusting the pop-up window strategy to optimize the user experience.

[0102] Reference Figure 2 An embodiment of the present invention provides a general game pop-up window configuration system 2, and the system 2 specifically includes:

[0103] The first configuration module 201 is used to set a unified pop-up window protocol, and determine the data format, calling method and interaction process of each terminal access according to the pop-up window protocol;

[0104] The second configuration module 202 is used to establish a mapping relationship between multiple game business scenarios and pop-up window configuration parameters, and manage pop-up window content according to the mapping relationship. The pop-up window configuration parameters include pop-up window style parameters and content editing rules;

[0105] The third configuration module 203 is used to form a pop-up window triggering rule set according to the pop-up window triggering conditions, target groups and contact opportunities of each game business scenario, and based on the pop-up window triggering rule set, determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up through a rule matching algorithm;

[0106] The fourth configuration module 204 is used to dynamically control the pop-up window triggering frequency of each user by mining the association between the user behavior pattern and the factors affecting the pop-up window effect.

[0107] It is understandable that if Figure 1 The contents of the configuration method of the general game pop-up window shown in the embodiment are applicable to the configuration system embodiment of the general game pop-up window. The functions specifically implemented by the configuration system embodiment of the general game pop-up window are similar to those of the embodiment of the general game pop-up window. Figure 1 The configuration method of the general game pop-up window shown in the embodiment is the same as that of the embodiment shown in the embodiment, and the beneficial effects achieved are the same as those of the embodiment shown in the embodiment. Figure 1 The beneficial effects achieved by the embodiment of the configuration method of the general game pop-up window shown are also the same.

[0108] It should be noted that the information interaction, execution process and other contents between the above-mentioned systems are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0109] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0110] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a configuration method for a general game pop-up window as described in any one of the above methods is implemented.

[0111] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0112] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0113] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0114] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for configuring a general game pop-up window as described in any one of the above methods is implemented.

[0115] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill 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 to be beyond the scope of this application.

[0118] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A method for configuring a general game pop-up window, characterized in that: The method specifically comprises: Set a unified pop-up window protocol, and determine the data format, calling method and interaction process of each terminal access according to the pop-up window protocol; Establishing a mapping relationship between multiple game business scenarios and pop-up window configuration parameters, and managing pop-up window content according to the mapping relationship, wherein the pop-up window configuration parameters include pop-up window style parameters and content editing rules; A pop-up window triggering rule set is formed according to the pop-up window triggering conditions, target groups and contact timing of each game business scenario. Based on the pop-up window triggering rule set, a rule matching algorithm is used to determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up; By exploring the correlation between user behavior patterns and factors affecting pop-up effects, the pop-up triggering frequency of each user can be dynamically controlled.

2. The method according to claim 1, characterized in that Determining the data format, calling method and interaction process of each terminal access according to the pop-up window protocol specifically includes: According to the pop-up window protocol, combined with the platform characteristics and technical conditions of each terminal, design a preliminary implementation plan for the pop-up window function; Conduct platform compatibility testing on the preliminary implementation plan of the pop-up window function to obtain display effects and user experience under different operating systems and device models, and obtain compatibility test results; Analyze the compatibility test results using a decision tree algorithm to find out the key factors affecting cross-platform compatibility and obtain test analysis results; According to the test analysis results, the preliminary implementation plan of the pop-up window function is optimized to determine the data format, calling method and interaction process of each terminal access.

3. The method according to claim 1, characterized in that The establishing of mapping relationships between multiple game business scenarios and pop-up window configuration parameters, and managing pop-up window content according to the mapping relationships, specifically includes: Determine corresponding pop-up window configuration parameters according to characteristic attributes of different game business scenarios, summarize characteristic attributes of each game business scenario and its corresponding pop-up window configuration parameters, and form a pop-up window configuration database; Obtain new game business scenarios, use K-means clustering algorithm to perform cluster analysis on the new game business scenarios and existing game business scenarios, and determine the existing game business scenarios that are most similar to the new game business scenarios; Based on the existing game service scenario that is most similar to the new game service scenario, a pop-up window configuration parameter corresponding to the new game service scenario is acquired from the pop-up window configuration database.

4. The method according to claim 1, characterized in that: The method of determining in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up based on the pop-up window triggering rule set by a rule matching algorithm specifically includes: Convert the pop-up window triggering rule set into a decision tree, use each pop-up window triggering rule condition as a node of the decision tree, use the ID3 algorithm to train and optimize the decision tree, and generate a rule decision tree model; Acquire user behavior data and game status data in real time, match the user behavior data and the game status data with the rule decision tree model, and obtain the pop-up priority of the pop-up information; Based on the pop-up priority, push appropriate pop-up information to the target user, and obtain the target user's feedback data on the pop-up information that has been displayed, the feedback data including the number of clicks, the number of closes and the length of stay; Associating the feedback data with the corresponding pop-up window triggering rules, and analyzing them using an association rule mining algorithm to obtain an association pattern between the pop-up window triggering rules and user feedback; The rule decision tree model is optimized and adjusted according to the association rules.

5. The method according to claim 1, characterized in that The method of dynamically controlling the pop-up window triggering frequency of each user by mining the correlation between the user behavior pattern and the factors affecting the pop-up window effect specifically includes: Obtain user historical behavior data and pop-up window historical display data, wherein the user historical behavior data includes user attributes, browsing tracks and interactive behaviors, and the pop-up window historical display data includes pop-up window attributes, display timing, display frequency and click conversion; After extracting feature vectors from the user historical behavior data and the pop-up window historical display data and merging the feature vectors, an Apriori algorithm is used to perform association rule mining to obtain an association rule set between user behavior unfamiliarity and pop-up window effects; Based on the association rule set, a logistic regression model is used to establish a mapping relationship between user behavior patterns and pop-up window effects, and a binary classification model is trained. The binary classification model is used to predict the acceptance degree and conversion probability of the pop-up windows by different users in different scenarios; Based on the binary classification model, the optimal triggering timing and frequency of the pop-up window for each user in any scenario are determined.

6. The method according to claim 5, characterized in that The method further comprises: Build a user profile according to the user's historical behavior data, and design multiple sets of pop-up window strategy solutions based on the user profile; Through the A / B testing method, conduct comparative experiments on different groups of pop-up strategy solutions to obtain feedback data on the strategy effects; According to the feedback data of the strategy effect, a reinforcement learning algorithm is used to optimize and adjust the binary classification model.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Obtain historical time series data for each pop-up window, and use a moving average method to establish multi-dimensional indicator data for each pop-up window type based on the historical time series data; By setting the time window size, determine a number of time windows; By judging in real time whether the indicator data of the pop-up window type corresponding to any pop-up window in the current time window exceeds the preset threshold range, it is determined whether the pop-up window is an abnormal pop-up window.

8. A general game pop-up configuration system, characterized in that: The system specifically comprises: The first configuration module is used to set a unified pop-up window protocol, and determine the data format, calling method and interaction process of each terminal access according to the pop-up window protocol; A second configuration module is used to establish a mapping relationship between multiple game business scenarios and pop-up window configuration parameters, and manage pop-up window content according to the mapping relationship. The pop-up window configuration parameters include pop-up window style parameters and content editing rules; The third configuration module is used to form a pop-up window triggering rule set according to the pop-up window triggering conditions, target groups and contact opportunities of each game business scenario, and based on the pop-up window triggering rule set, determine in real time whether a pop-up window is needed and the priority of the pop-up window information to be popped up through a rule matching algorithm; The fourth configuration module is used to dynamically control the pop-up window triggering frequency of each user by mining the correlation between user behavior patterns and factors affecting pop-up window effects.

9. A computer device, characterized in that: include: A memory, a processor and a computer program stored in the memory, when the computer program is executed on the processor, implements the configuration method of the universal game pop-up window as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the configuration method of a general game pop-up window as described in any one of claims 1 to 7 is implemented.

Images