Multi-ecology user dynamic growth level management method and device based on pan-entertainment, equipment and storage medium

Abstract

The invention provides a multi-ecology user dynamic growth level management method and device based on pan-entertainment, equipment and a storage medium, user behavior data is asynchronously collected through a message queue, a user behavior feature vector containing multiple behavior type feature values is constructed, and a multi-ecology user dynamic growth level management algorithm is established based on the feature vector. User points are calculated through weighted operation of configuration weights and dynamic adjustment coefficients, historical points and monthly points are combined through the weight coefficients to obtain a comprehensive score, and balance evaluation of long-term value and short-term activeness of users is achieved. Determining a user grade through a grade mapping function according to the comprehensive score, dynamically adjusting a grade state based on upgrading and grade preservation conditions, and updating a dynamic adjustment coefficient in real time according to user grade change and contribution degrees of various behavior types to form a self-adaptive grade management closed loop; and the system can automatically learn and optimize the importance degrees of different behavior types, so that a real fair and intelligent user value evaluation system is realized.

Description

Technical Field

[0001] The present invention relates to the field of platform user management, and in particular to a method, device, equipment and storage medium for dynamic user growth level management based on pan-entertainment multi-ecology. Background Art

[0002] With the booming development of the internet's pan-entertainment industry, diverse business scenarios such as live streaming, social networking, and gaming are constantly emerging. User rating systems have become a core mechanism for enhancing user engagement and promoting the prosperity of platform ecosystems. Effective user rating management not only incentivizes user engagement but also creates greater commercial value for platforms. However, existing user rating management technologies have significant shortcomings in addressing multi-scenario and multi-dimensional user behavior assessment.

[0003] Existing user ranking systems generally employ a single-dimensional evaluation system, primarily relying on user payment amounts to calculate rankings. This ignores the value of users' contributions in other dimensions, such as content creation, social interaction, and platform activity. This mechanism not only easily leads to an unbalanced ecosystem where "paying is the key to success," but also deprives a large number of valuable but low-paying users of growth motivation. Furthermore, the traditional linear point accumulation method lacks a dynamic adjustment mechanism, failing to truly reflect users' current activity levels and resulting in a rigid ranking system.

[0004] In view of this, this application is filed. Summary of the Invention

[0005] The present invention discloses a method, device, equipment and storage medium for dynamic growth level management of users based on pan-entertainment multi-ecology, aiming to achieve comprehensive quantification of the multi-dimensional behavioral value of users to truly reflect the current active status of users.

[0006] The first embodiment of the present invention provides a method for managing user dynamic growth levels based on pan-entertainment multi-ecology, including: Asynchronously collect user behavior data in multiple scenarios and services through message queues, and construct a user behavior feature vector containing feature values ​​of various behavior types; Based on the user behavior feature vector, user points are calculated by weighted operation using configured weights and dynamic adjustment coefficients, the user points are added to the historical points and monthly points respectively, and the historical points and monthly points are combined using the historical points weight coefficient to calculate a comprehensive score; Determine the user level through a level mapping function based on the comprehensive score, determine whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and update the user level status and level validity period accordingly; According to the changes in user level and the contribution of each behavior type in the user behavior feature vector, the dynamic adjustment coefficient corresponding to each behavior type is updated through an iterative algorithm controlled by a learning rate, and the updated dynamic adjustment coefficient is applied to the integral calculation of the next cycle to form an adaptive level management closed loop.

[0007] Preferably, the calculation process of the user points is to multiply each eigenvalue in the user behavior feature vector by the corresponding configuration weight and dynamic adjustment coefficient, and sum all weighted eigenvalues ​​to obtain the user points. The specific expression is:

[0008] in, is the configuration weight of the ith behavior, is the characteristic value of the i-th behavior, m is the total number of behavior types, is the dynamic adjustment coefficient; The comprehensive score is calculated by weighted sum of historical points and monthly points, and its expression is:

[0009] in, For the comprehensive score, is the historical integral weight coefficient, is the historical score, Monthly points.

[0010] Preferably, the iterative algorithm controlled by the learning rate updates the dynamic adjustment coefficient corresponding to each behavior type, specifically: Calculate the level difference between the current cycle and the previous cycle as the level change, and calculate the proportion of the characteristic value of each behavior type to the total characteristic values ​​as the contribution of the behavior type; Multiply the level change, contribution, and learning rate, and add them to the original dynamic adjustment coefficient to get a new dynamic adjustment coefficient, which is expressed as follows:

[0011] in, is the level of the current cycle, is the level of the previous cycle, For contribution, is the current dynamic adjustment coefficient, is the updated dynamic adjustment coefficient, is the learning rate of the current cycle.

[0012] Preferably, the learning rate adopts an adaptive adjustment strategy, which increases the learning rate when the level changes in the same direction twice in a row, and decreases the learning rate when the levels change in opposite directions, specifically:

[0013] in, is the adjustment factor, is a symbolic function, is the level change trend of the current cycle, This is the level change trend of the previous cycle.

[0014] Preferably, it also includes: Calculate the user's points acquisition rate within a fixed time window. When it is determined that the points acquisition rate exceeds the average rate plus n times the standard deviation, mark the user as an abnormal user, multiply all dynamic adjustment coefficients of the abnormal user by a preset multiple penalty factor, and regularly calculate the user retention rate. Optimize the configuration weight of each behavior type based on the retention rate change trend.

[0015] Preferably, it also includes: The CRC32 hash algorithm is used to calculate the user's unique identifier. The calculation result is modulo 32 to determine the shard number to which the user data belongs. A historical points table and a monthly points table are created for each shard. The table name is generated by the formatting function. The Redis distributed lock mechanism is used to ensure the atomicity of user level updates. The lock key value is composed of the user's unique identifier, level value, and update timestamp.

[0016] The second embodiment of the present invention provides a device for managing user dynamic growth levels based on pan-entertainment multi-ecology, including: A behavior data acquisition unit is used to asynchronously collect user behavior data in multiple scenarios and services through a message queue, and construct a user behavior feature vector containing feature values ​​of multiple behavior types; a comprehensive score calculation unit, configured to calculate user points based on the user behavior feature vector by weighted operation using configured weights and dynamic adjustment coefficients, add the user points to the historical points and monthly points respectively, and combine the historical points and monthly points using the historical points weight coefficient to calculate a comprehensive score; a level management unit, configured to determine the user level through a level mapping function according to the comprehensive score, determine whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and update the user level status and level validity period accordingly; The parameter adjustment unit is used to update the dynamic adjustment coefficient corresponding to each behavior type through an iterative algorithm controlled by a learning rate according to the changes in the user level and the contribution of each behavior type in the user behavior feature vector, and apply the updated dynamic adjustment coefficient to the integral calculation of the next cycle to form an adaptive level management closed loop.

[0017] The third embodiment of the present invention provides a device for dynamic growth level management of users based on pan-entertainment and multi-ecology, characterized in that it includes a memory and a processor, the memory stores a computer program, and the computer program can be executed by the processor to implement a method for dynamic growth level management of users based on pan-entertainment and multi-ecology as described in any one of the above items.

[0018] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that it stores a computer program, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a method for dynamic growth level management of users based on pan-entertainment multi-ecology as described in any one of the above items.

[0019] Based on the method, device, equipment and storage medium for dynamic user growth level management based on pan-entertainment multi-ecology provided by the present invention, user behavior data is asynchronously collected through a message queue, and a user behavior feature vector containing characteristic values ​​of multiple behavior types is constructed. Based on the feature vector, user points are calculated by weighted operations with configured weights and dynamic adjustment coefficients. Historical points and monthly points are combined with weight coefficients to obtain a comprehensive score, thus achieving a balanced assessment of the user's long-term value and short-term activity. The user level is determined by a level mapping function based on the comprehensive score, and the level status is dynamically adjusted based on the upgrade and relegation conditions. The dynamic adjustment coefficient is updated in real time according to the changes in user level and the contribution of each behavior type, forming an adaptive level management closed loop, so that the system can automatically learn and optimize the importance of different behavior types, thereby realizing a truly fair and intelligent user value evaluation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flowchart of a method for managing dynamic user growth levels based on pan-entertainment multi-ecology provided by the first embodiment of the present invention; Figure 2 This is a module diagram of a device for managing dynamic user growth levels based on pan-entertainment and multi-ecology provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] The present invention discloses a method, device, equipment and storage medium for dynamic growth level management of users based on pan-entertainment multi-ecology, aiming to achieve comprehensive quantification of the multi-dimensional behavioral value of users to truly reflect the current active status of users.

[0023] A first embodiment of the present invention provides a method for managing the dynamic growth level of users based on a pan-entertainment multi-ecology system. The method can be executed by a device for managing the dynamic growth level of users based on a pan-entertainment multi-ecology system (hereinafter referred to as a management device or system). Specifically, the method is executed by one or more processors within the management device or system to implement at least the following steps: S101, asynchronously collecting user behavior data in multiple scenarios and services through a message queue, and constructing a user behavior feature vector containing feature values ​​of multiple behavior types; In this embodiment, the management device can be a terminal with data processing capabilities such as a laptop computer, desktop computer, server workstation, etc. The management device can be installed with a corresponding operating system and application software, and the functions required by this embodiment can be realized through the combination of the operating system and application software.

[0024] This embodiment uses the Pulsar message queue as the core component of data collection to build an asynchronous data processing architecture with multiple producers and multiple consumers. In various business scenarios of the pan-entertainment platform, including live broadcast scenarios, chat room scenarios, family scenarios and social scenarios, when a user generates any behavior, the corresponding business system will encapsulate the behavior into a message event and push it to the Pulsar queue. For example, when a user gives a virtual gift in the live broadcast room, the live broadcast system will generate a message containing information such as user ID, gift type, gift value, and gift time; when a user interacts with the microphone in the chat room, the chat room system will record the user's microphone start time and end time, calculate the microphone duration, and generate a corresponding behavior event message.

[0025] Each behavior event is standardized into a unified data structure when entering the Pulsar queue, consisting of three core attributes: event occurrence time, behavior type enumeration value, and behavior value. The behavior type enumeration value uses a predefined coding system. For example, virtual gift giving is coded as 1, recharge amount is coded as 2, item consumption is coded as 3, PK result is coded as 4, live broadcast duration is coded as 5, viewing duration is coded as 6, leaderboard ranking is coded as 7, and family check-in is coded as 8. The behavior value has different meanings depending on the behavior type. For example, the behavior value of virtual gift giving is the gift value (unit: yuan), the behavior value of live broadcast duration is the duration (unit: seconds), and the behavior value of PK result may include the rule of 1 point for victory, 0.5 points for draw, and 0 points for loss.

[0026] During data collection, the system filters behavioral events in real time using business filtering rules configured in Redis. For example, for virtual gift giving, a minimum amount threshold of 0.1 yuan might be set, filtering out gifts below this threshold. For live broadcast duration statistics, a minimum valid duration of 30 seconds might be set, preventing calls shorter than this from counting towards points. This filtering mechanism is implemented through an indicator function, which returns 1 if the behavior meets the configured business conditions and 0 otherwise.

[0027] For filtered behavior data, the system will assign a personal behavior bonus based on the user's unique identity or the special items used. For example, if a user uses a 1.2x points card, the personal bonus coefficient for all their actions will be 1.2; if a user uses a 2x experience item during a specific event, the bonus coefficient will be 2.0. The system multiplies the filtered behavior value by the personal bonus coefficient to determine the added value of the behavior.

[0028] When constructing user behavior feature vectors, the system maintains an 8-dimensional vector for each user, with each dimension corresponding to a specific behavior type. Within a statistical period (e.g., one day), the system continuously accumulates the numerical values ​​of similar behaviors generated by users in various scenarios. For example, a user might give gifts in multiple livestream rooms in a single day, and the system would sum the values ​​of all gifts as the feature value for the virtual gift giving dimension. A user might also go on the microphone multiple times in different chat rooms, and the system would sum the duration of all sessions as the feature value for the duration of the livestream connection dimension.

[0029] S102: Calculate user points based on the user behavior feature vector by weighted operation using configured weights and dynamic adjustment coefficients, add the user points to the historical points and monthly points, and combine the historical points and monthly points using the historical points weight coefficient to calculate a comprehensive score; After the system obtains the user behavior feature vector, it needs to convert these multi-dimensional behavior data into a unified integral value. In this embodiment, the system uses weighted aggregation to calculate points. Specifically, the system maintains a set of weight configuration tables in the etcd configuration center, and sets corresponding weight coefficients for each behavior type. For example, in actual operation, the weight of virtual gift giving may be set to 0.3, indicating that this behavior accounts for 30% of the overall points calculation; the weight of the recharge amount may be set to 0.2; and non-paid behaviors such as the length of the microphone connection and the length of viewing may each have a weight of 0.1-0.15. These weight configurations can be set accordingly based on actual conditions. In this implementation, not only the user's paid contribution is valued, but also the value of the user in content creation, social interaction, etc. is recognized.

[0030] In addition to fixed configuration weights, the system also introduces a dynamic adjustment coefficient mechanism. Each behavior type has a separate dynamic adjustment coefficient, initially set to 1.0. This coefficient automatically adjusts based on the user's level, enabling adaptive optimization of the points strategy. For example, if the system finds that a user primarily earns points by watching live streams but their level is improving slowly, the dynamic adjustment coefficient for that user's viewing time may be appropriately increased to encourage continued activity.

[0031] When calculating user points, the system traverses each dimension of the user behavior feature vector, multiplies the feature value, configuration weight and dynamic adjustment coefficient, and then sums the results of all dimensions (the specific expression is: For example, if a user's behavioral feature vector during a statistical period is [600, 100, 50, 2, 180, 300, 5, 7], the corresponding configuration weights are [0.3, 0.2, 0.1, 0.05, 0.1, 0.1, 0.1, 0.05], and the dynamic adjustment coefficients are all 1.0, then the user's points calculation process is: 600×0.3×1.0 + 100×0.2×1.0 + 50×0.1×1.0 + 2×0.05×1.0 + 180×0.1×1.0 + 300×0.1×1.0 + 5×0.1×1.0 + 7×0.05×1.0 = 253.45 points.

[0032] After earning a single point, the system needs to update the user's historical points and monthly points. Historical points are cumulative, meaning each calculated point is added to the user's historical points total. This value accumulates continuously from the time the user registers, representing the user's long-term value contribution on the platform. Monthly points reset to 0 on the first day of each calendar month, and all points accumulated during the month are added to the monthly points, reflecting the user's short-term activity.

[0033] In order to balance long-term value and short-term activity, the system combines the two to calculate a comprehensive score using the historical score weight coefficient β (the expression is: In this embodiment, the value of β is typically set between 0.3 and 0.7, with the specific value determined based on the platform's operational strategy. For example, when β = 0.4, historical points account for 40% of the overall score, and monthly points account for 60%. This protects the vested interests of existing users while providing growth space for new and reactivated users.

[0034] S103, determining the user level through a level mapping function based on the comprehensive score, determining whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and updating the user level status and level validity period accordingly; The system uses a segmented mapping approach to convert users' comprehensive scores into specific level values. A level mapping table is stored in the etcd configuration center, defining the score ranges corresponding to each level. For example, 0-999 points corresponds to Level 1, 1000-4999 points corresponds to Level 2, 5000-19999 points corresponds to Level 3, and so on, up to the preset level cap.

[0035] After determining a user's base level, the system further considers monthly points to determine promotions and demotions. Historical points determine a user's base level, while monthly points determine whether the user can maintain or upgrade their current level. In practice, the system sets both an upgrade threshold and a retention threshold for each level. The upgrade threshold is typically the same as or slightly higher than the upper limit for that level, while the retention threshold is set at 60% of the previous level's upper limit. For example, a Level 3 user might have a threshold of 20,000 points for upgrades and a retention threshold of 3,000 points (60% of the Level 2 upper limit of 5,000 points).

[0036] The system executes level determination logic after each points update. It first checks whether the user's monthly points have reached the upgrade threshold. If so, the user's level is raised by one level, and the level validity period is set to the end of the following month. This longer protection period is designed to reward users who actively upgrade, giving them ample time to enjoy the benefits of the new level. If the monthly points do not reach the upgrade threshold but meet the level retention requirements, the system will maintain the user's current level, but the validity period will only be extended to the end of the following month. This protects the user's vested interests while maintaining a certain level of activeness.

[0037] For users who meet neither the upgrade nor the retention requirements, the system will not downgrade them immediately. Instead, it will be processed uniformly at dawn on the first day of each month through a scheduled task. This batch processing method avoids the negative user experience caused by frequent level changes. During the downgrade process, the system will recalculate the user's level based on their actual monthly points, potentially reducing their level by one or more levels until their monthly points meet the retention requirements.

[0038] S104, based on the changes in user level and the contribution of each behavior type in the user behavior feature vector, the dynamic adjustment coefficient corresponding to each behavior type is updated through an iterative algorithm controlled by a learning rate, and the updated dynamic adjustment coefficient is applied to the integral calculation of the next cycle to form an adaptive level management closed loop.

[0039] After a user completes a cycle (e.g., a day) of behavioral data statistics, the system calculates the user's level change. By comparing the current level with the level from the previous cycle, the level change is calculated. This change can be positive (upgrade), zero (retention), or negative (downgrade), directly reflecting the incentive effect of the current points strategy on the user. Simultaneously, the system analyzes the contribution of each dimension in the user's behavioral feature vector, calculating the proportion of each behavior type's feature value to the total feature value. For example, if a user's virtual gift giving feature value is 600, and the sum of all behavioral feature values ​​is 1000, the contribution of virtual gift giving is 0.6, indicating that 60% of the user's points come from gift giving.

[0040] Based on the level change and behavior contribution, the system uses a gradient-ascending approach to update the dynamic adjustment coefficient. If the user's level increases, it means the current points strategy is effective, and the system will strengthen the behavior types with high contribution and appropriately increase their dynamic adjustment coefficients. Conversely, if the user's level decreases, the system will reduce the adjustment coefficients of the main contributing behaviors, while possibly increasing the coefficients of other behavior types, guiding users to engage in more diverse platform activities. This update is achieved by multiplying the level change, contribution, and learning rate, and then adding them to the original adjustment coefficient. Its expression is: .

[0041] The learning rate plays a role in controlling the step size during the entire update process. The specific expression is: The system uses an adaptive learning rate strategy, dynamically adjusting the learning rate by analyzing the level change trends over two consecutive cycles. If the system detects two consecutive level changes in the same direction (e.g., two consecutive upgrades or two consecutive downgrades), it indicates that the current adjustment direction is correct, and the system multiplies the learning rate by an adjustment factor of 1.2 to accelerate convergence. Conversely, if the level changes in the opposite direction (e.g., an upgrade followed by a downgrade), it indicates that over-adjustment may have occurred, and the system multiplies the learning rate by 0.8 to slow down the adjustment and avoid system oscillation.

[0042] In practice, this adaptive mechanism has demonstrated promising results. For example, if a user who primarily earns points through top-ups experiences a prolonged stagnation in their level, the system will gradually reduce the dynamic adjustment coefficient for top-up behavior while simultaneously increasing the coefficients for other behaviors, such as content creation and social interaction, to encourage more comprehensive participation in platform activities. For highly active users with diverse behaviors, the system will maintain a relative balance among these coefficients, ensuring they can achieve growth through a variety of channels.

[0043] The updated dynamic adjustment coefficient is immediately applied to the next cycle's points calculation, forming a real-time feedback loop. This enables the system to automatically optimize the points strategy based on each user's behavioral characteristics and growth trajectory, avoiding "one-size-fits-all" and extensive management while reducing the need for manual intervention. Through continuous learning and adjustment, the system will ultimately find the most appropriate combination of incentive parameters for each user, enabling a personalized level growth path.

[0044] In a possible implementation of the present invention, the present invention further includes: Calculate the user's points acquisition rate within a fixed time window. When it is determined that the points acquisition rate exceeds the average rate plus n times the standard deviation, mark the user as an abnormal user, multiply all dynamic adjustment coefficients of the abnormal user by a preset multiple penalty factor, and regularly calculate the user retention rate. Optimize the configuration weight of each behavior type based on the retention rate change trend.

[0045] It should be noted that the system continuously monitors each user's points acquisition status through a sliding time window. In this embodiment, the time window is set to 24 hours, and the system calculates the user's point acquisition rate over the past 24 hours once every hour. During the specific calculation, the system reads the user's points value at the start and end of the time window from the database, and the difference between the two divided by the time interval is the point acquisition rate. For example, if a user's points increase from 1000 to 2500 in 24 hours, their point acquisition rate is 62.5 points / hour.

[0046] To identify anomalous behavior, the system maintains a global statistical model for point acquisition rates. This model calculates the average point acquisition rate and standard deviation for all active users in real time. In actual operations, we've found that while the point acquisition rate of normal users follows a roughly normal distribution, the rate of malicious users deviates significantly from the normal range. Based on this characteristic, the system employs the statistical 3σ principle for anomaly detection. When a user's point acquisition rate exceeds the mean plus three standard deviations, the system automatically marks them as an anomaly. This effectively identifies malicious behavior while avoiding misjudgments of normally active users.

[0047] For users marked as abnormal, the system will not directly ban or reset their points. Instead, it will adopt a more moderate restriction strategy. Specifically, the dynamic adjustment coefficient for all behavior types of the user will be multiplied by a penalty factor of 0.5. This means that all subsequent points earned by the abnormal user will be halved, which serves as a penalty while also giving the user an opportunity to correct their behavior. If the user returns to normal behavior during the subsequent observation period, the system will gradually lift the restrictions and gradually restore the penalty factor from 0.5 to 1.0.

[0048] In addition to anomaly detection, the system also optimizes the overall points strategy by analyzing user retention rates. At the beginning of each month, the system calculates the percentage of users who registered or were active 30 days ago who are still active. This percentage is the monthly retention rate. By comparing retention rate data for consecutive months, the system can evaluate the effectiveness of the current points strategy. If the retention rate shows a downward trend, there may be problems with the current incentive mechanism, and the configuration weights of each behavior type need to be adjusted.

[0049] Weight optimization is implemented using A / B testing combined with machine learning. The system randomly divides users into multiple experimental groups, assigning slightly different weightings to each group. For example, Group A receives a higher weighting for non-paying behaviors, while Group B receives a higher weighting for social interactions. After a testing cycle, the system analyzes core metrics such as retention, activity, and paid conversions for each group, selecting the best-performing weighting and rolling it out to all users. This ensures that the ranking system remains aligned with user needs and platform development goals, enabling continuous evolution and optimization of the system.

[0050] In a possible implementation of the present invention, the present invention further includes: The CRC32 hash algorithm is used to calculate the user's unique identifier. The calculation result is modulo 32 to determine the shard number to which the user data belongs. A historical points table and a monthly points table are created for each shard. The table name is generated by the formatting function. The Redis distributed lock mechanism is used to ensure the atomicity of user level updates. The lock key value is composed of the user's unique identifier, level value, and update timestamp.

[0051] When user data needs to be stored or queried, the system first performs a CRC32 hash on the user's UUID. A UUID is a 32-bit unique identifier generated by the platform for each user, consisting of numbers, letters, and underscores. The CRC32 algorithm converts this string into a 32-bit integer value, then performs a modulo operation on it to obtain a shard number between 0 and 31. For example, if the user UUID is "a1b2c3d4_e5f6g7h8_i9j0k1l2_m3n4o5p6", the CRC32 hash value will be 2147483647, which is then used to obtain shard number 31. All data for this user will be stored in shard number 31.

[0052] The system creates two types of data tables for each shard: a historical points table and a monthly points table. Table names are generated using the sprintf formatting function, following the naming convention of "radiant_" plus the four-digit shard number. For example, the historical points table for shard 0 is named "radiant_0000," and the monthly points table for shard 31 is named "radiant_0031." This ensures the standardization of table names and facilitates operations and maintenance personnel to quickly locate data. Each table contains core fields such as user UUID, points value, and update time. The historical points table records the user's accumulated points since registration, while the monthly points table is reset and recalculated at the beginning of each month.

[0053] During the critical operation of updating a user's rank, the system must ensure data consistency and atomicity. In a distributed environment, multiple service instances may simultaneously process the same user's request. Without proper concurrency control, duplicate rank upgrades or inconsistent data can occur. To this end, the system employs the Redis distributed lock mechanism for protection.

[0054] When a user's level needs to be updated, the system first constructs a lock key value. The lock key value consists of three parts: user UUID, target level value, and current timestamp, separated by a colon. For example, to upgrade user "a1b2c3d4_e5f6g7h8_i9j0k1l2_m3n4o5p6" to level 5, At timestamp 1625097600, the lock key value is: "a1b2c3d4_e5f6g7h8_i9j0k1l2_m3n4o5p6:5:1625097600". Ensure that each level change has a unique lock identifier to avoid duplicate processing.

[0055] The system attempts to acquire the lock using the Redis SETNX command, which succeeds only if the key doesn't already exist. If the lock is successfully acquired, the system performs the level update, including updating the user's level table in MySQL, recording the level change log, and sending a level change notification. After the operation is complete, the lock is released. If the lock acquisition fails, it indicates that another process is already processing the user's level update, and the current request will be rejected or retried. The lock expiration time is set to 30 seconds, which ensures sufficient time for normal operations to complete while avoiding deadlocks caused by exceptions.

[0056] The second embodiment of the present invention provides a device for managing user dynamic growth levels based on pan-entertainment multi-ecology, including: The behavior data acquisition unit 201 is used to asynchronously collect user behavior data in multiple scenarios and services through a message queue, and construct a user behavior feature vector containing feature values ​​of multiple behavior types; A comprehensive score calculation unit 202 is configured to calculate user points based on the user behavior feature vector by configuring weights and dynamic adjustment coefficients, add the user points to the historical points and monthly points respectively, and combine the historical points and monthly points using the historical points weight coefficient to calculate a comprehensive score; The level management unit 203 is configured to determine the user level through a level mapping function based on the comprehensive score, determine whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and update the user level status and level validity period accordingly; The parameter adjustment unit 204 is used to update the dynamic adjustment coefficient corresponding to each behavior type through an iterative algorithm controlled by a learning rate according to the changes in the user level and the contribution of each behavior type in the user behavior feature vector, and apply the updated dynamic adjustment coefficient to the integral calculation of the next cycle to form an adaptive level management closed loop.

[0057] The third embodiment of the present invention provides a device for dynamic growth level management of users based on pan-entertainment and multi-ecology, characterized in that it includes a memory and a processor, the memory stores a computer program, and the computer program can be executed by the processor to implement a method for dynamic growth level management of users based on pan-entertainment and multi-ecology as described in any one of the above items.

[0058] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that it stores a computer program, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a method for dynamic growth level management of users based on pan-entertainment multi-ecology as described in any one of the above items.

[0059] Based on the method, device, equipment and storage medium for dynamic user growth level management based on pan-entertainment multi-ecology provided by the present invention, user behavior data is collected asynchronously through a message queue, and a user behavior feature vector containing characteristic values ​​of multiple behavior types is constructed. Based on the feature vector, user points are calculated by weighted operations with configured weights and dynamic adjustment coefficients, and historical points and monthly points are combined through weight coefficients to obtain a comprehensive score, thereby achieving a balanced assessment of the user's long-term value and short-term activity. The user level is determined by a level mapping function based on the comprehensive score, and the level status is dynamically adjusted based on the upgrade and relegation conditions. The dynamic adjustment coefficient is updated in real time according to the changes in the user level and the contribution of each behavior type, forming an adaptive level management closed loop, so that the system can automatically learn and optimize the importance of different behavior types, thereby realizing a truly fair and intelligent user value evaluation system. Exemplarily, the computer program described in the third and fourth embodiments of the present invention can be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the device for implementing a dynamic user growth level management device based on pan-entertainment multi-ecology. For example, the device described in the second embodiment of the present invention.

[0060] The processor 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. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the method for dynamic user growth level management based on pan-entertainment multi-ecology, and utilizes various interfaces and lines to connect the various parts of the method for dynamic user growth level management based on pan-entertainment multi-ecology.

[0061] The memory can be used to store the computer programs and / or modules. The processor implements various functions of a method for managing dynamic user growth levels in a pan-entertainment multi-ecosystem by running or executing the computer programs and / or modules stored in the memory and accessing data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as audio playback or text conversion); the data storage area may store data generated based on the use of the mobile phone (such as audio data and text message data). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0062] If the implemented module is implemented as 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 invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0063] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0064] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for dynamic user growth level management based on pan-entertainment multi-ecology, characterized in that: include: Asynchronously collect user behavior data in multiple scenarios and services through message queues, and construct a user behavior feature vector containing feature values ​​of various behavior types; Based on the user behavior feature vector, user points are calculated by weighted operation using configured weights and dynamic adjustment coefficients, the user points are added to the historical points and monthly points respectively, and the historical points and monthly points are combined using the historical points weight coefficient to calculate a comprehensive score; Determine the user level through a level mapping function based on the comprehensive score, determine whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and update the user level status and level validity period accordingly; According to the changes in user level and the contribution of each behavior type in the user behavior feature vector, the dynamic adjustment coefficient corresponding to each behavior type is updated through an iterative algorithm controlled by a learning rate, and the updated dynamic adjustment coefficient is applied to the integral calculation of the next cycle to form an adaptive level management closed loop.

2. A method for managing user dynamic growth levels based on pan-entertainment multi-ecology according to claim 1, characterized in that: The calculation process of the user points is to multiply each eigenvalue in the user behavior feature vector by the corresponding configuration weight and dynamic adjustment coefficient, and sum all weighted eigenvalues ​​to obtain the user points. The specific expression is: in, is the configuration weight of the ith behavior, is the characteristic value of the i-th behavior, m is the total number of behavior types, is the dynamic adjustment coefficient; The comprehensive score is calculated by weighted sum of historical points and monthly points, and its expression is: in, For the comprehensive score, is the historical integral weight coefficient, is the historical integral, Monthly points.

3. A method for managing user dynamic growth levels based on pan-entertainment multi-ecology according to claim 1, characterized in that: The iterative algorithm controlled by the learning rate updates the dynamic adjustment coefficient corresponding to each behavior type, specifically: Calculate the level difference between the current cycle and the previous cycle as the level change, and calculate the proportion of the characteristic value of each behavior type to the total characteristic values ​​as the contribution of the behavior type; Multiply the level change, contribution, and learning rate, and add them to the original dynamic adjustment coefficient to get a new dynamic adjustment coefficient, which is expressed as follows: in, is the level of the current cycle, is the level of the previous cycle, For contribution, is the current dynamic adjustment coefficient, is the updated dynamic adjustment coefficient, is the learning rate of the current cycle.

4. A method for managing user dynamic growth levels based on pan-entertainment multi-ecology according to claim 3, characterized in that: The learning rate adopts an adaptive adjustment strategy. When the level changes in the same direction twice in a row, the learning rate is increased, and when the directions are opposite, the learning rate is reduced. Specifically: in, is the adjustment factor, is a symbolic function, is the level change trend of the current cycle, This is the level change trend of the previous cycle.

5. The method for managing user dynamic growth levels based on pan-entertainment multi-ecology according to claim 1 is characterized in that: Also includes: Calculate the user's points acquisition rate within a fixed time window. When it is determined that the points acquisition rate exceeds the average rate plus n times the standard deviation, mark the user as an abnormal user, multiply all dynamic adjustment coefficients of the abnormal user by a preset multiple penalty factor, and regularly calculate the user retention rate. Optimize the configuration weight of each behavior type based on the retention rate change trend.

6. A method for managing user dynamic growth levels based on pan-entertainment multi-ecology according to claim 1, characterized in that: Also includes: The CRC32 hash algorithm is used to calculate the user's unique identifier. The calculation result is modulo 32 to determine the shard number to which the user data belongs. A historical points table and a monthly points table are created for each shard. The table name is generated by the formatting function. The Redis distributed lock mechanism is used to ensure the atomicity of user level updates. The lock key value is composed of the user's unique identifier, level value, and update timestamp.

7. A device for managing user dynamic growth levels based on pan-entertainment and multi-ecology, characterized in that: include: A behavior data acquisition unit is used to asynchronously collect user behavior data in multiple scenarios and services through a message queue, and construct a user behavior feature vector containing feature values ​​of multiple behavior types; a comprehensive score calculation unit, configured to calculate user points based on the user behavior feature vector by weighted operation using configured weights and dynamic adjustment coefficients, add the user points to the historical points and monthly points respectively, and combine the historical points and monthly points using the historical points weight coefficient to calculate a comprehensive score; a level management unit, configured to determine the user level through a level mapping function according to the comprehensive score, determine whether the user meets the upgrade or level retention conditions based on the current level and the monthly points, and update the user level status and level validity period accordingly; The parameter adjustment unit is used to update the dynamic adjustment coefficient corresponding to each behavior type through an iterative algorithm controlled by a learning rate according to the changes in the user level and the contribution of each behavior type in the user behavior feature vector, and apply the updated dynamic adjustment coefficient to the integral calculation of the next cycle to form an adaptive level management closed loop.

8. A device for managing user dynamic growth levels based on pan-entertainment and multi-ecology, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a method for dynamic growth level management of users based on pan-entertainment multi-ecology as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that A computer program is stored, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a method for dynamic growth level management of users based on pan-entertainment multi-ecology as described in any one of claims 1 to 6.

Images