Method and system for dynamic balance of mobile games based on behavior analysis and performance adaptation

Abstract

This application provides a method and system for dynamic balancing of mobile games based on behavior analysis and performance adaptation. The method includes: real-time collection of target player's operation flow data and game performance data, obtaining the target player's historical operation data; processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density; determining whether cheating behavior exists based on the effective operation density and taking corresponding action; obtaining device operating data and adjusting image quality parameters accordingly; matching a corresponding dynamic difficulty coefficient based on historical operation data and device operating data; and optimizing the matching pool weight allocation logic, thereby achieving dynamic balancing of mobile games based on behavior analysis and performance adaptation.

Description

Technical Field

[0001] This application relates to the field of mobile game balancing technology, and more specifically, to a method and system for dynamic balancing of mobile games based on behavior analysis and performance adaptation. Background Technology

[0002] Current mobile game dynamic balance adjustments mostly rely on preset rules or single data indicators (such as win rate and kill count), lacking comprehensive consideration of player operation characteristics and device operating status. Traditional methods are prone to adjustment lag and cannot effectively identify the interference of cheating behavior on balance, affecting the fairness of the game.

[0003] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for dynamic balancing of mobile games based on behavior analysis and performance adaptation. This method can collect the target player's operation flow data and game performance data in real time, and obtain the target player's historical operation data. Based on the operation flow data, game performance data, and historical operation data, and combined with device performance thresholds, it can obtain an effective operation density. Based on the effective operation density, it can determine whether there is cheating behavior and take corresponding actions. It can also obtain device operation data and adjust the image quality parameters accordingly. Based on historical operation data and device operation data, it can match the corresponding dynamic difficulty coefficient and optimize the matching pool weight allocation logic, thereby realizing the technology of dynamic balancing of mobile games based on behavior analysis and performance adaptation.

[0005] This application also provides a dynamic balancing method for mobile games based on behavior analysis and performance adaptation, including the following steps:

[0006] Real-time collection of target player's action flow data and game performance data, and acquisition of target player's historical action data;

[0007] Based on the operation flow data, game performance data, and historical operation data, and combined with the device performance threshold, an effective operation density is obtained;

[0008] Based on the effective operation density, determine whether cheating has occurred and take appropriate action.

[0009] Acquire device operating data and adjust image quality parameters accordingly;

[0010] Based on the historical operation data and equipment operation data, a corresponding dynamic difficulty coefficient is matched, and the matching pool weight allocation logic is optimized.

[0011] Optionally, in the mobile game dynamic balancing method based on behavior analysis and performance adaptation described in this application, the real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, includes:

[0012] Real-time collection of target player's action flow data and game performance data;

[0013] The operation flow data includes touch trajectory and skill release interval;

[0014] The match performance data includes damage conversion rate and time spent at map points;

[0015] Obtain the target player's historical action data, including the average historical effective action density and the fluctuation range of historical effective action density.

[0016] Optionally, in the mobile game dynamic balancing method based on behavior analysis and performance adaptation described in this application, the step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes:

[0017] Based on the touch trajectory, skill release interval, damage conversion rate, and dwell time at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model.

[0018] Obtain the device performance threshold and compare it with the preset threshold.

[0019] If the device performance threshold is less than a preset threshold, the player's operation density is corrected to obtain an effective operation density;

[0020] If the device performance threshold is greater than or equal to a preset threshold, then the player operation density is the effective operation density.

[0021] Optionally, in the mobile game dynamic balancing method based on behavior analysis and performance adaptation described in this application, the step of determining whether cheating behavior exists based on the effective operation density and performing corresponding processing includes:

[0022] Obtain a preset operation density threshold that matches the target player;

[0023] The effective operating density is compared with a preset operating density threshold.

[0024] If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal.

[0025] If the effective operation density is greater than or equal to the preset operation density threshold, the target player's operation is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

[0026] Optionally, in the mobile game dynamic balancing method based on behavior analysis and performance adaptation described in this application, the step of acquiring device operating data and adjusting image quality parameters accordingly includes:

[0027] Acquire device operating data, including memory usage and GPU rendering latency;

[0028] The device operating status coefficient is obtained by weighting the memory usage rate and GPU rendering latency.

[0029] Adjust the image quality parameters according to the device operating status coefficient;

[0030] The image quality parameters include texture resolution, shadow quality, and the number of particle effects.

[0031] Optionally, in the mobile game dynamic balancing method based on behavior analysis and performance adaptation described in this application, the step of matching the corresponding dynamic difficulty coefficient based on the historical operation data and device operation data, and optimizing the matching pool weight allocation logic, includes:

[0032] Based on the historical average effective operation density and the historical effective operation density fluctuation range, combined with the memory usage rate and GPU rendering latency, a dynamic difficulty coefficient is obtained by processing through a preset difficulty setting model.

[0033] Game parameter settings are matched according to the dynamic difficulty coefficient;

[0034] The matching pool weight allocation logic is optimized based on the dynamic difficulty coefficient.

[0035] Secondly, this application provides a mobile game dynamic balancing system based on behavior analysis and performance adaptation. The system includes a memory and a processor. The memory includes a program for a mobile game dynamic balancing method based on behavior analysis and performance adaptation. When the program for the mobile game dynamic balancing method based on behavior analysis and performance adaptation is executed by the processor, it performs the following steps:

[0036] Real-time collection of target player's action flow data and game performance data, and acquisition of target player's historical action data;

[0037] Based on the operation flow data, game performance data, and historical operation data, and combined with the device performance threshold, an effective operation density is obtained;

[0038] Based on the effective operation density, determine whether cheating has occurred and take appropriate action.

[0039] Acquire device operating data and adjust image quality parameters accordingly;

[0040] Based on the historical operation data and equipment operation data, a corresponding dynamic difficulty coefficient is matched, and the matching pool weight allocation logic is optimized.

[0041] Optionally, in the mobile game dynamic balancing system based on behavior analysis and performance adaptation described in this application, the real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, includes:

[0042] Real-time collection of target player's action flow data and game performance data;

[0043] The operation flow data includes touch trajectory and skill release interval;

[0044] The match performance data includes damage conversion rate and time spent at map points;

[0045] Obtain the target player's historical action data, including the average historical effective action density and the fluctuation range of historical effective action density.

[0046] Optionally, in the mobile game dynamic balancing system based on behavior analysis and performance adaptation described in this application, the step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes:

[0047] Based on the touch trajectory, skill release interval, damage conversion rate, and dwell time at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model.

[0048] Obtain the device performance threshold and compare it with the preset threshold.

[0049] If the device performance threshold is less than a preset threshold, the player's operation density is corrected to obtain an effective operation density;

[0050] If the device performance threshold is greater than or equal to a preset threshold, then the player operation density is the effective operation density.

[0051] Optionally, in the mobile game dynamic balancing system based on behavior analysis and performance adaptation described in this application, the step of determining whether cheating behavior exists based on the effective operation density and performing corresponding processing includes:

[0052] Obtain a preset operation density threshold that matches the target player;

[0053] The effective operating density is compared with a preset operating density threshold.

[0054] If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal.

[0055] If the effective operation density is greater than or equal to the preset operation density threshold, the target player's operation is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

[0056] As can be seen from the above, the mobile game dynamic balancing method and system based on behavior analysis and performance adaptation provided in this application collects the target player's operation flow data and game performance data in real time, and obtains the target player's historical operation data. Based on the operation flow data, game performance data, and historical operation data, and combined with device performance thresholds, the system processes the data to obtain an effective operation density. Based on the effective operation density, it determines whether there is cheating behavior and takes corresponding actions. It also obtains device operation data and adjusts the image quality parameters accordingly. Based on the historical operation data and device operation data, it matches the corresponding dynamic difficulty coefficient and optimizes the matching pool weight allocation logic, thereby realizing the technology of mobile game dynamic balancing based on behavior analysis and performance adaptation.

[0057] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 A flowchart of a mobile game dynamic balancing method based on behavior analysis and performance adaptation provided in this application embodiment;

[0060] Figure 2 A flowchart illustrating the effective operation density of a mobile game dynamic balancing method based on behavior analysis and performance adaptation provided in this application embodiment;

[0061] Figure 3 A flowchart illustrating the determination of whether cheating behavior exists in the mobile game dynamic balancing method based on behavior analysis and performance adaptation provided in this application embodiment;

[0062] Figure 4 The flowchart illustrates the process of adjusting image quality parameters for stable transmission in a mobile game dynamic balancing method based on behavior analysis and performance adaptation, as provided in this application embodiment. Detailed Implementation

[0063] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0064] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0065] Please refer to Figure 1 , Figure 1 This is a flowchart of a mobile game dynamic balancing method based on behavior analysis and performance adaptation, as described in some embodiments of this application. This method is used in terminal devices such as computers and mobile phones. The method includes the following steps:

[0066] S11. Real-time collection of the target player's operation flow data and game performance data, and acquisition of the target player's historical operation data;

[0067] S12. Based on the operation flow data, game performance data and historical operation data, and combined with the device performance threshold, the effective operation density is obtained.

[0068] S13. Determine whether cheating occurs based on the effective operation density and take appropriate action.

[0069] S14. Obtain device operation data and adjust image quality parameters accordingly;

[0070] S15. Based on the historical operation data and equipment operation data, match the corresponding dynamic difficulty coefficient and optimize the matching pool weight allocation logic.

[0071] It should be noted that existing dynamic balancing systems cannot simultaneously analyze player operation patterns and device performance, leading to adjustments that deviate from the actual experience. Cheating tools interfere with balance determination, and traditional anti-cheat technologies struggle to identify abnormal behavior disguised as normal operations in real time. To address these challenges, firstly, real-time collection of target player operation flow data, including touch trajectories and skill release intervals, as well as match performance data, including damage conversion rate and time spent at map points, is employed. Historical operation data of the target player is also obtained, including the average historical effective operation density and its fluctuation range. Based on the operation flow data, match performance data, and historical operation data, combined with device performance thresholds, effective operation density is obtained. Different players playing different games correspond to different operation density limits; therefore, the existence of cheating behavior is determined based on the effective operation density, and appropriate action is taken. Device operation data is acquired, and corresponding image quality parameters, including texture resolution, shadow quality, and particle effect quantity, are adjusted. Based on historical operation data and device operation data, a corresponding dynamic difficulty coefficient is matched, and the matchmaking pool weight allocation logic is optimized, thereby achieving a mobile game dynamic balancing technology based on behavior analysis and performance adaptation.

[0072] According to an embodiment of the present invention, the real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, includes:

[0073] Real-time collection of target player's action flow data and game performance data;

[0074] The operation flow data includes touch trajectory and skill release interval;

[0075] The match performance data includes damage conversion rate and time spent at map points;

[0076] Obtain the target player's historical action data, including the average historical effective action density and the fluctuation range of historical effective action density.

[0077] It should be noted that the system collects real-time operation flow data and game performance data of the target players. Operation flow data focuses on the player's real-time interactive behavior. Touch trajectory data records the screen click coordinate sequence, swipe speed, and duration to accurately reconstruct the operation path, such as the player's swipe amplitude and direction changes in the virtual joystick area. Skill release interval data calculates the time difference between two releases of the same skill, including the shortest and average intervals for consecutive releases, reflecting the player's control over skill cooldown rhythm. Game performance data evaluates player performance from the perspective of actual combat effectiveness. Damage conversion rate calculates the ratio of the player's total output damage to the total skill consumption, reflecting the effectiveness of the operation, such as the percentage of damage dealt to enemy heroes by skills. Map location dwell time records the cumulative dwell time of players in key areas (such as resource points and high-incidence areas of team fights) to analyze their tactical selection tendencies. At the same time, the target player's historical operation data is retrieved as a reference benchmark. The average historical effective operation density is the average of effective operations per unit time within a preset period (such as 7 days), reflecting the player's long-term operation intensity. The fluctuation range of historical effective operation density is calculated using standard deviation to reflect the player's operation stability and provide data support for subsequent difficulty adjustments.

[0078] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the method for obtaining effective operation density in mobile games based on behavior analysis and performance adaptation, as described in some embodiments of this application. According to embodiments of the present invention, the step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes:

[0079] S21. Based on the touch trajectory, skill release interval, damage conversion rate, and time spent at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model.

[0080] S22. Obtain the device performance threshold and compare it with the preset defined threshold;

[0081] S23. If the device performance threshold is less than the preset threshold, the player operation density is corrected to obtain an effective operation density.

[0082] S24. If the device performance threshold is greater than or equal to the preset threshold, then the player operation density is the effective operation density.

[0083] It's important to note that calculating player action density requires comprehensive consideration of multiple key data points. First, there's the player's real-time action information during gameplay, including touch trajectories, which reflect the fluidity and precision of their actions, such as the smoothness of finger swipes and the accuracy of clicks. Skill release intervals are also crucial; the length and stability of these intervals demonstrate the player's control over skill rhythm. Damage conversion rate directly shows the actual effect of actions, i.e., the efficiency with which input is converted into damage against the enemy. Finally, there's the duration of time spent at map points, reflecting the player's utilization and control of map resources and strategic locations. This real-time action data is then combined with the player's historical average effective action density and its fluctuation range, and further processed systematically using a pre-defined player action baseline model. This baseline model is based on a large number of player action data points. The system is designed to weight, compare, and analyze various data points to generate the player's current operation density. This density provides a preliminary quantification of the player's current activity and effectiveness. Simultaneously, the system automatically reads the performance threshold of the running device and compares it with the game's preset device performance threshold. If the actual device performance threshold is lower than the preset threshold, it indicates hardware limitations, requiring dynamic correction of the previously generated player operation density. A compensation algorithm eliminates invalid operation data caused by device lag, ultimately yielding an effective operation density reflecting the player's true skill level. If the device performance threshold reaches or exceeds the preset threshold, it indicates sufficient hardware performance to support operational precision; in this case, the initially calculated player operation density can be directly used as the effective operation density.

[0084] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the determination of cheating behavior using a mobile game dynamic balancing method based on behavior analysis and performance adaptation, as described in some embodiments of this application. According to embodiments of the present invention, the step of determining whether cheating behavior exists based on the effective operation density and performing corresponding processing includes:

[0085] S31. Obtain a preset operation density limit threshold that matches the target player;

[0086] S32. Compare the effective operating density with the preset operating density threshold.

[0087] S33. If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal.

[0088] S34. If the effective operation density is greater than or equal to the preset operation density threshold, the operation of the target player is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

[0089] It's important to note that the system first determines the appropriate operation density threshold based on the target player's game rank, historical playstyle, and frequently used hero types. This threshold is derived by analyzing a large amount of normal operation data from players of the same skill level, accurately reflecting the reasonable range of operational intensity for that group. Next, the system quantitatively compares the previously calculated effective operation density with this threshold. If the effective operation density is lower than the threshold, it indicates that the player's operation frequency and intensity are within the normal range, consistent with the general performance of players of the same skill level, thus determining that the target player's operation is normal. Conversely, if the effective operation density reaches or exceeds the threshold, it means that the player's operational rhythm, reaction speed, and other indicators have exceeded the reasonable range for players of the same skill level, suggesting the possibility of using cheats such as hacks to improve operational efficiency. In this case, the system immediately marks the player as a suspected cheater and triggers further verification mechanisms, such as manual review of operation recordings and detection of background program anomalies, to ultimately confirm whether cheating has occurred.

[0090] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the adjustment of image quality parameters in a mobile game dynamic balancing method based on behavior analysis and performance adaptation, as described in some embodiments of this application. According to embodiments of the present invention, the step of acquiring device operating data and adjusting image quality parameters accordingly includes:

[0091] S41. Obtain device operating data, including memory usage and GPU rendering latency;

[0092] S42. Perform weighted processing based on the memory usage rate and GPU rendering latency to obtain the device operating status coefficient;

[0093] S43. Adjust the image quality parameters according to the device operating status coefficient;

[0094] S44. The image quality parameters include texture resolution, shadow quality, and particle effect quantity.

[0095] It's important to note that the system monitors and acquires device performance data in real time through background processes. Two key metrics are particularly critical: memory usage and GPU rendering latency. Memory usage, calculated as the ratio of currently used memory to total memory, directly reflects the device's memory resource constraints. High usage can lead to sluggish application response or even crashes. GPU rendering latency refers to the time required for the graphics processor to complete the rendering of a frame from receiving rendering instructions. A higher latency indicates slower image generation, potentially causing stuttering, frame drops, and other issues that negatively impact the user experience. After acquiring these two metrics, the system performs weighted processing based on different preset weights according to the device's hardware configuration. For example, for devices with limited memory, the weight of memory usage is appropriately increased; while for devices that prioritize graphics processing, the weight of GPU rendering latency is more prominent. After weighted calculation using a formula, a comprehensive quantitative value is obtained, known as the device's operating status coefficient. This coefficient typically fluctuates between 0 and 1. The closer the coefficient is to 1, the greater the current operating pressure on the device, and the closer its performance is to its limit; the closer the coefficient is to 0, the less demanding the device is. The system operates smoothly with ample performance reserves. Subsequently, it automatically adjusts various image quality parameters based on the device's operating status coefficient. These parameters include texture resolution, shadow quality, and particle effect quantity. For example, when the device operating status coefficient is high (e.g., above 0.7), to alleviate hardware pressure, the system reduces texture resolution, making the detailed textures of objects in the image relatively blurry; lowers shadow quality, making shadow edges rougher and layers simpler; and reduces the number of particle effects, such as reducing the particle density of flames and reducing the diffusion range of smoke. When the coefficient is low (e.g., below 0.3), the system increases texture resolution, making the textures of walls, floors, etc., clearer; increases shadow quality, making shadows present more natural transitions and delicate layers; and increases the number of particle effects, making skill releases, explosion scenes, etc., more gorgeous and realistic. If the coefficient is at a moderate level between 0.3 and 0.7, the system will maintain a balance of image quality parameters, maintaining a good visual effect as much as possible while ensuring smooth operation.

[0096] According to an embodiment of the present invention, the step of matching a corresponding dynamic difficulty coefficient based on the historical operation data and device operation data, and optimizing the matching pool weight allocation logic, includes:

[0097] Based on the historical average effective operation density and the historical effective operation density fluctuation range, combined with the memory usage rate and GPU rendering latency, a dynamic difficulty coefficient is obtained by processing through a preset difficulty setting model.

[0098] Game parameter settings are matched according to the dynamic difficulty coefficient;

[0099] The matching pool weight allocation logic is optimized based on the dynamic difficulty coefficient.

[0100] It's important to note that the model combines the average historical effective operation density and its fluctuation range with memory usage and GPU rendering latency to input a preset difficulty setting. The model uses a multi-layered algorithm for weighted fusion: historical operation data has a higher weight (approximately 60%), ensuring the difficulty benchmark accurately reflects the player's actual skill level; device performance data accounts for approximately 40%, used to dynamically compensate for the impact of hardware limitations on operations. For example, if a player's historical average operation density is high but current GPU latency is too high, the model will appropriately reduce the difficulty to compensate for the operational obstacles caused by lag, ultimately outputting a dynamic difficulty coefficient of 0-10, with higher values ​​indicating higher recommended difficulty. Then, based on the dynamic difficulty coefficient, the system will match corresponding game parameter settings, such as enemy AI strength and mission completion tolerance, ensuring the game difficulty matches the player's ability and device status. Furthermore, the system will optimize the matchmaking pool's weight allocation logic based on this coefficient, increasing the probability of players being matched with opponents of similar skill levels and device performance, thus improving game fairness and user experience.

[0101] Secondly, the present invention also discloses a mobile game dynamic balancing system based on behavior analysis and performance adaptation, including a memory and a processor. The memory includes a mobile game dynamic balancing method program based on behavior analysis and performance adaptation. When the mobile game dynamic balancing method program based on behavior analysis and performance adaptation is executed by the processor, it performs the following steps:

[0102] Real-time collection of target player's action flow data and game performance data, and acquisition of target player's historical action data;

[0103] Based on the operation flow data, game performance data, and historical operation data, and combined with the device performance threshold, an effective operation density is obtained;

[0104] Based on the effective operation density, determine whether cheating has occurred and take appropriate action.

[0105] Acquire device operating data and adjust image quality parameters accordingly;

[0106] Based on the historical operation data and equipment operation data, a corresponding dynamic difficulty coefficient is matched, and the matching pool weight allocation logic is optimized.

[0107] It should be noted that existing dynamic balancing systems cannot simultaneously analyze player operation patterns and device performance, leading to adjustments that deviate from the actual experience. Cheating tools interfere with balance determination, and traditional anti-cheat technologies struggle to identify abnormal behavior disguised as normal operations in real time. To address these challenges, firstly, real-time collection of target player operation flow data, including touch trajectories and skill release intervals, as well as match performance data, including damage conversion rate and time spent at map points, is employed. Historical operation data of the target player is also obtained, including the average historical effective operation density and its fluctuation range. Based on the operation flow data, match performance data, and historical operation data, combined with device performance thresholds, effective operation density is obtained. Different players playing different games correspond to different operation density limits; therefore, the existence of cheating behavior is determined based on the effective operation density, and appropriate action is taken. Device operation data is acquired, and corresponding image quality parameters, including texture resolution, shadow quality, and particle effect quantity, are adjusted. Based on historical operation data and device operation data, a corresponding dynamic difficulty coefficient is matched, and the matchmaking pool weight allocation logic is optimized, thereby achieving a mobile game dynamic balancing technology based on behavior analysis and performance adaptation.

[0108] According to an embodiment of the present invention, the real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, includes:

[0109] Real-time collection of target player's action flow data and game performance data;

[0110] The operation flow data includes touch trajectory and skill release interval;

[0111] The match performance data includes damage conversion rate and time spent at map points;

[0112] Obtain the target player's historical action data, including the average historical effective action density and the fluctuation range of historical effective action density.

[0113] It should be noted that the system collects real-time operation flow data and game performance data of the target players. Operation flow data focuses on the player's real-time interactive behavior. Touch trajectory data records the screen click coordinate sequence, swipe speed, and duration to accurately reconstruct the operation path, such as the player's swipe amplitude and direction changes in the virtual joystick area. Skill release interval data calculates the time difference between two releases of the same skill, including the shortest and average intervals for consecutive releases, reflecting the player's control over skill cooldown rhythm. Game performance data evaluates player performance from the perspective of actual combat effectiveness. Damage conversion rate calculates the ratio of the player's total output damage to the total skill consumption, reflecting the effectiveness of the operation, such as the percentage of damage dealt to enemy heroes by skills. Map location dwell time records the cumulative dwell time of players in key areas (such as resource points and high-incidence areas of team fights) to analyze their tactical selection tendencies. At the same time, the target player's historical operation data is retrieved as a reference benchmark. The average historical effective operation density is the average of effective operations per unit time within a preset period (such as 7 days), reflecting the player's long-term operation intensity. The fluctuation range of historical effective operation density is calculated using standard deviation to reflect the player's operation stability and provide data support for subsequent difficulty adjustments.

[0114] According to an embodiment of the present invention, the step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes:

[0115] Based on the touch trajectory, skill release interval, damage conversion rate, and dwell time at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model.

[0116] Obtain the device performance threshold and compare it with the preset threshold.

[0117] If the device performance threshold is less than a preset threshold, the player's operation density is corrected to obtain an effective operation density;

[0118] If the device performance threshold is greater than or equal to a preset threshold, then the player operation density is the effective operation density.

[0119] It's important to note that calculating player action density requires comprehensive consideration of multiple key data points. First, there's the player's real-time action information during gameplay, including touch trajectories, which reflect the fluidity and precision of their actions, such as the smoothness of finger swipes and the accuracy of clicks. Skill release intervals are also crucial; the length and stability of these intervals demonstrate the player's control over skill rhythm. Damage conversion rate directly shows the actual effect of actions, i.e., the efficiency with which input is converted into damage against the enemy. Finally, there's the duration of time spent at map points, reflecting the player's utilization and control of map resources and strategic locations. This real-time action data is then combined with the player's historical average effective action density and its fluctuation range, and further processed systematically using a pre-defined player action baseline model. This baseline model is based on a large number of player action data points. The system is designed to weight, compare, and analyze various data points to generate the player's current operation density. This density provides a preliminary quantification of the player's current activity and effectiveness. Simultaneously, the system automatically reads the performance threshold of the running device and compares it with the game's preset device performance threshold. If the actual device performance threshold is lower than the preset threshold, it indicates hardware limitations, requiring dynamic correction of the previously generated player operation density. A compensation algorithm eliminates invalid operation data caused by device lag, ultimately yielding an effective operation density reflecting the player's true skill level. If the device performance threshold reaches or exceeds the preset threshold, it indicates sufficient hardware performance to support operational precision; in this case, the initially calculated player operation density can be directly used as the effective operation density.

[0120] According to an embodiment of the present invention, the step of determining whether cheating behavior exists based on the effective operation density and performing corresponding processing includes:

[0121] Obtain a preset operation density threshold that matches the target player;

[0122] The effective operating density is compared with a preset operating density threshold.

[0123] If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal.

[0124] If the effective operation density is greater than or equal to the preset operation density threshold, the target player's operation is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

[0125] It's important to note that the system first determines the appropriate operation density threshold based on the target player's game rank, historical playstyle, and frequently used hero types. This threshold is derived by analyzing a large amount of normal operation data from players of the same skill level, accurately reflecting the reasonable range of operational intensity for that group. Next, the system quantitatively compares the previously calculated effective operation density with this threshold. If the effective operation density is lower than the threshold, it indicates that the player's operation frequency and intensity are within the normal range, consistent with the general performance of players of the same skill level, thus determining that the target player's operation is normal. Conversely, if the effective operation density reaches or exceeds the threshold, it means that the player's operational rhythm, reaction speed, and other indicators have exceeded the reasonable range for players of the same skill level, suggesting the possibility of using cheats such as hacks to improve operational efficiency. In this case, the system immediately marks the player as a suspected cheater and triggers further verification mechanisms, such as manual review of operation recordings and detection of background program anomalies, to ultimately confirm whether cheating has occurred.

[0126] According to an embodiment of the present invention, the step of acquiring device operating data and adjusting image quality parameters accordingly includes:

[0127] Acquire device operating data, including memory usage and GPU rendering latency;

[0128] The device operating status coefficient is obtained by weighting the memory usage rate and GPU rendering latency.

[0129] Adjust the image quality parameters according to the device operating status coefficient;

[0130] The image quality parameters include texture resolution, shadow quality, and the number of particle effects.

[0131] It's important to note that the system monitors and acquires device performance data in real time through background processes. Two key metrics are particularly critical: memory usage and GPU rendering latency. Memory usage, calculated as the ratio of currently used memory to total memory, directly reflects the device's memory resource constraints. High usage can lead to sluggish application response or even crashes. GPU rendering latency refers to the time required for the graphics processor to complete the rendering of a frame from receiving rendering instructions. A higher latency indicates slower image generation, potentially causing stuttering, frame drops, and other issues that negatively impact the user experience. After acquiring these two metrics, the system weights them according to the device's hardware configuration. For example, for devices with limited memory, memory usage is weighted more heavily, while GPU rendering latency is given greater weight for devices that prioritize graphics processing. The weighted calculation yields a comprehensive quantitative value, the device performance coefficient, which typically fluctuates between 0 and 1. The closer the coefficient is to 1, the higher the device's current operating pressure. The greater the force, the closer the performance is to its limit; the closer the coefficient is to 0, the smoother the device runs and the more performance reserves it has. Subsequently, the system will automatically adjust various image quality parameters based on the device's operating status coefficient. These parameters specifically include texture resolution, shadow quality, and the number of particle effects. For example, when the device's operating status coefficient is high (e.g., above 0.7), to alleviate hardware pressure, the system will reduce texture resolution, making the detailed textures of objects in the image relatively blurry; lower shadow quality, making shadow edges rougher and the layers simpler; and reduce the number of particle effects, such as reducing the particle density of flames and reducing the diffusion range of smoke. When the coefficient is low (e.g., below 0.3), the system will increase texture resolution, making the textures of walls, floors, etc. clearer; increase shadow quality, making shadows present a more natural transition and delicate layers; and increase the number of particle effects, making skill releases, explosion scenes, etc. more gorgeous and realistic. If the coefficient is at a moderate level between 0.3 and 0.7, the system will maintain a balance of image quality parameters, maintaining a good visual effect as much as possible while ensuring smooth operation.

[0132] According to an embodiment of the present invention, the step of matching a corresponding dynamic difficulty coefficient based on the historical operation data and device operation data, and optimizing the matching pool weight allocation logic, includes:

[0133] Based on the historical average effective operation density and the historical effective operation density fluctuation range, combined with the memory usage rate and GPU rendering latency, a dynamic difficulty coefficient is obtained by processing through a preset difficulty setting model.

[0134] Game parameter settings are matched according to the dynamic difficulty coefficient;

[0135] The matching pool weight allocation logic is optimized based on the dynamic difficulty coefficient.

[0136] It's important to note that the model combines the average historical effective operation density and its fluctuation range with memory usage and GPU rendering latency to input a preset difficulty setting. The model uses a multi-layered algorithm for weighted fusion: historical operation data has a higher weight (approximately 60%), ensuring the difficulty benchmark accurately reflects the player's actual skill level; device performance data accounts for approximately 40%, used to dynamically compensate for the impact of hardware limitations on operations. For example, if a player's historical average operation density is high but current GPU latency is too high, the model will appropriately reduce the difficulty to compensate for the operational obstacles caused by lag, ultimately outputting a dynamic difficulty coefficient of 0-10, with higher values ​​indicating higher recommended difficulty. Then, based on the dynamic difficulty coefficient, the system will match corresponding game parameter settings, such as enemy AI strength and mission completion tolerance, ensuring the game difficulty matches the player's ability and device status. Furthermore, the system will optimize the matchmaking pool's weight allocation logic based on this coefficient, increasing the probability of players being matched with opponents of similar skill levels and device performance, thus improving game fairness and user experience.

[0137] The present invention discloses a mobile game dynamic balancing method and system based on behavior analysis and performance adaptation. This method collects real-time operation flow data and game performance data of target players, and obtains their historical operation data. Based on the operation flow data, game performance data, and historical operation data, and combined with device performance thresholds, it processes the data to obtain an effective operation density. Based on the effective operation density, it determines whether cheating behavior exists and takes appropriate action. It also obtains device operating data and adjusts image quality parameters accordingly. Based on historical operation data and device operating data, it matches a corresponding dynamic difficulty coefficient and optimizes the matching pool weight allocation logic, thereby achieving mobile game dynamic balancing technology based on behavior analysis and performance adaptation.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0139] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0141] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0142] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A dynamic balancing method for mobile games based on behavior analysis and performance adaptation, characterized in that, Includes the following steps: Real-time collection of target player's action flow data and game performance data, and acquisition of target player's historical action data; Based on the operation flow data, game performance data, and historical operation data, and combined with the device performance threshold, an effective operation density is obtained; Based on the effective operation density, determine whether cheating has occurred and take appropriate action. Acquire device operating data and adjust image quality parameters accordingly; Based on the historical operation data and equipment operation data, a corresponding dynamic difficulty coefficient is matched, and the matching pool weight allocation logic is optimized. The real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, include: Real-time collection of target player's action flow data and game performance data; The operation flow data includes touch trajectory and skill release interval; The match performance data includes damage conversion rate and time spent at map points; Obtain the target player's historical operation data, including the average historical effective operation density and the fluctuation range of historical effective operation density; The step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes: Based on the touch trajectory, skill release interval, damage conversion rate, and dwell time at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model. Obtain the device performance threshold and compare it with the preset threshold. If the device performance threshold is less than a preset threshold, the player's operation density is corrected to obtain an effective operation density; If the device performance threshold is greater than or equal to the preset threshold, then the player operation density is the effective operation density. The step of determining whether cheating has occurred based on the effective operation density and taking corresponding action includes: Obtain a preset operation density threshold that matches the target player; The effective operating density is compared with a preset operating density threshold. If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal. If the effective operation density is greater than or equal to the preset operation density threshold, the target player's operation is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

2. The mobile game dynamic balancing method based on behavior analysis and performance adaptation according to claim 1, characterized in that, The process of acquiring device operating data and adjusting image quality parameters accordingly includes: Acquire device operating data, including memory usage and GPU rendering latency; The device operating status coefficient is obtained by weighting the memory usage rate and GPU rendering latency. Adjust the image quality parameters according to the device operating status coefficient; The image quality parameters include texture resolution, shadow quality, and the number of particle effects.

3. The mobile game dynamic balancing method based on behavior analysis and performance adaptation according to claim 2, characterized in that, The step of matching a corresponding dynamic difficulty coefficient based on the historical operation data and device operation data, and optimizing the matching pool weight allocation logic, includes: Based on the historical average effective operation density and the historical effective operation density fluctuation range, combined with the memory usage rate and GPU rendering latency, a dynamic difficulty coefficient is obtained by processing through a preset difficulty setting model. Game parameter settings are matched according to the dynamic difficulty coefficient; The matching pool weight allocation logic is optimized based on the dynamic difficulty coefficient.

4. A mobile game dynamic balancing system based on behavior analysis and performance adaptation, characterized in that: The system includes a memory and a processor. The memory contains a program for a mobile game dynamic balancing method based on behavior analysis and performance adaptation. When the program for the mobile game dynamic balancing method based on behavior analysis and performance adaptation is executed by the processor, it performs the following steps: Real-time collection of target player's action flow data and game performance data, and acquisition of target player's historical action data; Based on the operation flow data, game performance data, and historical operation data, and combined with the device performance threshold, an effective operation density is obtained; Based on the effective operation density, determine whether cheating has occurred and take appropriate action. Acquire device operating data and adjust image quality parameters accordingly; Based on the historical operation data and equipment operation data, a corresponding dynamic difficulty coefficient is matched, and the matching pool weight allocation logic is optimized. The real-time collection of the target player's operation flow data and game performance data, and the acquisition of the target player's historical operation data, include: Real-time collection of target player's action flow data and game performance data; The operation flow data includes touch trajectory and skill release interval; The match performance data includes damage conversion rate and time spent at map points; Obtain the target player's historical operation data, including the average historical effective operation density and the fluctuation range of historical effective operation density; The step of processing the operation flow data, game performance data, and historical operation data in conjunction with device performance thresholds to obtain effective operation density includes: Based on the touch trajectory, skill release interval, damage conversion rate, and dwell time at map points, combined with the average historical effective operation density and the fluctuation range of historical effective operation density, the player operation density is obtained by processing through a preset player operation baseline model. Obtain the device performance threshold and compare it with the preset threshold. If the device performance threshold is less than a preset threshold, the player's operation density is corrected to obtain an effective operation density; If the device performance threshold is greater than or equal to the preset threshold, then the player operation density is the effective operation density. The step of determining whether cheating has occurred based on the effective operation density and taking corresponding action includes: Obtain a preset operation density threshold that matches the target player; The effective operating density is compared with a preset operating density threshold. If the effective operation density is less than the preset operation density threshold, then the target player's operation is determined to be normal. If the effective operation density is greater than or equal to the preset operation density threshold, the target player's operation is determined to be abnormal, the target player is marked as a suspected cheater and further verification is performed.

Images