A method, device and equipment for intelligent automatic configuration of a member benefit scheme, and a storage medium

Abstract

The application provides a kind of intelligent automatic configuration method, device and equipment of member benefit scheme and storage medium, first, the benefit use record and consumption behavior record of target member user in platform are obtained from user database;Based on the benefit use record and the consumption behavior record, the benefit use feature and benefit preference feature of the target member user under different service context scenarios are extracted;According to the benefit use feature and the benefit preference feature, the benefit preference evidence of the target member user under each service context scenario is determined;Based on the benefit preference evidence under each service context scenario, the priority configuration benefit item of the target member user is determined, and then the priority configuration benefit item is used as the recommended benefit configuration result of the target member user.Based on the above scheme, the intelligent configuration of member benefit can be realized based on member behavior characteristics and preference characteristics, so as to improve the personalized matching accuracy of benefit configuration.

Description

Technical Field

[0001] This application relates to the field of membership rights management technology, and more specifically, to an intelligent automatic configuration method, apparatus, device, and storage medium for a membership rights scheme. Background Technology

[0002] With the continuous development of various online platforms and service systems, membership systems, as an important means to improve user activity and retention, are widely used in e-commerce, lifestyle services, content platforms and other fields. Platforms usually provide a variety of benefits to members of different levels or types, such as coupons, dedicated customer service, points rewards, and content privileges, in order to enhance user stickiness and brand loyalty. However, users' needs and usage behaviors for benefits vary in different service scenarios, making it difficult for a unified and fixed benefit distribution model to accurately meet individual needs. How to achieve personalized configuration of membership benefits has become an important direction in platform management.

[0003] In existing technologies, the configuration of membership benefits mainly relies on operation and maintenance strategies or user level tiers for unified allocation, lacking dynamic analysis based on specific user behavior data and preference characteristics. For example, different members often exhibit significant differences in the frequency of benefit usage, usage duration, and consumption behavior in different scenarios. However, existing solutions fail to establish a correspondence between benefit usage behavior and service context scenarios, nor do they identify potential benefit preferences from changes in user behavior. This results in benefit configuration outcomes that do not match users' actual needs, leading to low utilization rates of configured benefits, weakened user experience, and even waste of benefit resources. This is especially true in multi-scenario service platforms, where users exhibit differentiated preferences in different scenarios such as shopping, entertainment, learning, and social interaction, but traditional static configuration methods struggle to achieve scenario adaptation. Therefore, how to achieve intelligent configuration of membership benefits based on member behavior and preference characteristics, thereby improving the accuracy of personalized benefit matching, has become a challenge facing the industry. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for intelligent automatic configuration of membership benefits schemes, which can realize intelligent configuration of membership benefits based on member behavior characteristics and preference characteristics, thereby improving the accuracy of personalized matching of benefits configuration.

[0005] Firstly, this application provides an intelligent automatic configuration method for membership benefits schemes, comprising the following steps:

[0006] In response to the needs of configuring membership benefits, the system retrieves the usage records and consumption behavior records of target members on the platform from the user database.

[0007] Based on the rights usage records and the consumption behavior records, extract the rights usage characteristics and rights preference characteristics of the target member users in different service contexts;

[0008] Based on the rights usage characteristics and rights preference characteristics, evidence of the target member user's rights preference in each service context is determined;

[0009] Based on the evidence of rights and interests in each service context, the priority rights and interests of the target member user are determined, and then the priority rights and interests are used as the recommended rights and interests configuration result for the target member user.

[0010] In this embodiment, extracting the benefit usage characteristics and benefit preference characteristics of the target member user under different service contexts based on the benefit usage record and the consumption behavior record specifically includes:

[0011] The rights usage records are segmented by scenario tags to obtain the rights call frequency, usage duration and call sequence under each service context scenario;

[0012] The consumption behavior records are aggregated to obtain consumption amount, consumption cycle and interaction behavior features corresponding to each service context scenario;

[0013] By associating the frequency of rights calls, usage duration, and call sequence with the consumption amount, consumption cycle, and interaction behavior characteristics, the rights usage characteristics and rights preference characteristics of the target member users are extracted.

[0014] In this embodiment, the interactive behavior features include short-term interactive behavior features and long-term interactive behavior features.

[0015] In this embodiment, determining the evidence of the target member user's rights preference in various service contexts based on the rights usage characteristics and the rights preference characteristics specifically includes:

[0016] The rights usage characteristics and rights preference characteristics under each service context are weighted and fused according to multiple dimensions to obtain an initial preference score;

[0017] Based on the usage frequency of each benefit item in different time periods, the initial preference score is adjusted by a preset time decay function to reflect the dynamic impact of recent behavior on preference judgment;

[0018] The adjusted preference score is dynamically corrected based on the real-time attributes of the current service context, generating evidence of the target member user's rights and interests in each service context.

[0019] In this embodiment, the initial preference score is adjusted using a preset time decay function based on the usage frequency of each benefit item at different time periods to reflect the dynamic impact of recent behavior on preference judgment. Specifically, this includes:

[0020] Set a baseline decay coefficient and a time decay gradient, where the baseline decay coefficient corresponds to the reference validity of the most recent usage behavior, and the time decay gradient represents the decrease in the impact of usage behavior on the initial preference score as the time interval increases;

[0021] Calculate the time difference between the usage behavior of each right item and the current time, and reduce the benchmark decay coefficient according to the time difference and the time decay gradient to obtain the time decay factor of the behavior;

[0022] The time decay factor of the usage behavior of the rights and interests in each time period is applied to the adjustment of the initial preference score to obtain the dynamically updated initial preference score.

[0023] In this embodiment, the priority configuration benefits for the target member user are determined based on the benefit preference evidence in each service context scenario, specifically including:

[0024] The contribution coefficient of each benefit item to the benefit scenario is determined based on the benefit preference evidence in each service context.

[0025] By integrating the benefit scenario contribution coefficients of all service context scenarios, the benefit priority of each benefit item is obtained to reflect the target member users' preference for different benefit items;

[0026] All candidate benefits are sorted according to the benefit priority, and the benefit items with the highest ranking are selected as the priority benefit items for the target member user.

[0027] In this embodiment, the rights usage record includes data on the user's claiming, cancellation, and expiration of rights.

[0028] Secondly, this application provides an intelligent automatic configuration device for a membership benefits scheme. The system includes an intelligent configuration unit for membership benefits, which comprises:

[0029] The acquisition module is used to retrieve the target member's rights usage records and consumption behavior records on the platform from the user database in response to the member rights configuration requirements;

[0030] The processing module is used to extract the benefit usage characteristics and benefit preference characteristics of the target member user in different service contexts based on the benefit usage record and the consumption behavior record;

[0031] The processing module is further configured to determine the evidence of the target member user's rights preference in each service context based on the rights usage characteristics and the rights preference characteristics;

[0032] The execution module is used to determine the priority configuration rights of the target member user based on the rights preference evidence in each service context scenario, and then use the priority configuration rights as the recommended rights configuration result of the target member user.

[0033] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described intelligent automatic configuration method for the membership benefits scheme.

[0034] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent automatic configuration method for the membership benefits scheme.

[0035] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0036] This application provides an intelligent automatic configuration method, apparatus, device, and storage medium for a membership benefits scheme. In response to membership benefits configuration requirements, it retrieves the benefit usage records and consumption behavior records of target member users on the platform from a user database. Based on the benefit usage records and consumption behavior records, it extracts the benefit usage characteristics and benefit preference characteristics of the target member users in different service contexts. According to the benefit usage characteristics and benefit preference characteristics, it determines the benefit preference evidence of the target member users in each service context. Based on the benefit preference evidence in each service context, it determines the priority benefit items to be configured for the target member users, and then uses the priority benefit items as the recommended benefit configuration result for the target member users.

[0037] Therefore, this application determines the priority configuration items for the target member user based on the evidence of rights and interests in various service contexts, and then uses the priority configuration items as the recommended rights and interests configuration result for the target member user. First, based on rights and interests usage records and consumption behavior records, it extracts the rights and interests usage characteristics and rights and interests preference characteristics of the target member user in different service contexts. Through the rights and interests usage characteristics and rights and interests preference characteristics, it is possible to quantitatively describe the user's actual usage tendency and long-term preference trend, so that the configuration process can get rid of empirical rules and accurately present the user's attention and dependence on different rights and interests in a data-driven manner, thereby providing interpretable basic data support for subsequent preference determination. Second, based on the rights and interests usage characteristics and rights and interests preference characteristics, it determines the target member user's rights and interests in various service contexts. The system uses evidence of user preferences in different service contexts to reflect their varying preferences and intentions. This allows the system to identify the dynamic changes in a user's needs across different times and scenarios, avoiding the lack of personalization in traditional solutions that rely on a single preference label for uniform configuration. Then, based on this evidence, the system determines the priority rights for the target member user. Prioritizing these rights ensures that the most relevant and long-term preferences are presented or allocated, aligning recommendations with actual user needs and improving accessibility and satisfaction. In summary, this solution enables intelligent configuration of member rights based on behavioral and preference characteristics, thereby improving the accuracy of personalized rights matching. Attached Figure Description

[0038] Figure 1 This is an exemplary flowchart of an intelligent automatic configuration method for a membership benefits scheme according to some embodiments of this application;

[0039] Figure 2 This is an exemplary flowchart illustrating the determination of evidence of interest preference according to some embodiments of this application;

[0040] Figure 3 This is a schematic diagram of the structure of the intelligent configuration unit for membership rights shown in some embodiments of this application;

[0041] Figure 4 This is a schematic diagram of the structure of a computer device for implementing an intelligent automatic configuration method for membership benefits schemes according to some embodiments of this application. Detailed Implementation

[0042] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] refer to Figure 1 The figure is an exemplary flowchart of an intelligent automatic configuration method for a membership benefits scheme according to some embodiments of this application. The figure mainly includes the following steps:

[0044] In step 101, in response to the membership rights configuration requirements, the target member user's rights usage records and consumption behavior records on the platform are obtained from the user database.

[0045] In this embodiment, the system responds to member benefit configuration requests through a user database interface. First, it receives a configuration trigger signal from the platform to determine the identifier information of the target member user. Then, based on the identifier information, the system accesses a relational or non-relational user database to obtain the target member user's benefit usage records and consumption behavior records generated on the platform, including but not limited to benefit redemption, cancellation, and expiration data, as well as consumption amount, consumption time, consumption channel, and interaction behavior data. After obtaining the data, the system performs format standardization, missing value processing, and abnormal data removal to ensure the integrity and consistency of the data. Furthermore, the system can cache the processed data in a high-efficiency access storage medium to support subsequent extraction of benefit usage characteristics and preference characteristics, thereby providing a reliable data foundation for intelligent automatic configuration.

[0046] In step 102, based on the rights usage records and the consumption behavior records, the rights usage characteristics and rights preference characteristics of the target member user in different service contexts are extracted.

[0047] In this embodiment, the extraction of the benefit usage characteristics and benefit preference characteristics of the target member user under different service contexts based on the benefit usage record and the consumption behavior record can be achieved by the following steps:

[0048] The rights usage records are segmented by scenario tags to obtain the rights call frequency, usage duration and call sequence under each service context scenario;

[0049] The consumption behavior records are aggregated to obtain consumption amount, consumption cycle and interaction behavior features corresponding to each service context scenario;

[0050] By associating the frequency of rights calls, usage duration, and call sequence with the consumption amount, consumption cycle, and interaction behavior characteristics, the rights usage characteristics and rights preference characteristics of the target member users are extracted.

[0051] It should be noted that, in this application, the service context scenario refers to the specific service type and operating environment corresponding to a user's use of rights or consumption behavior on the platform; the frequency of rights invocation in this application refers to the number of times a user uses rights in a specific service scenario; the usage duration in this application describes the duration of a user's use of rights in a specific service scenario; the invocation sequence in this application refers to the order in which a user uses rights in a specific service scenario; the consumption cycle in this application refers to the time interval between user consumption behaviors in a specific service scenario; the interaction behavior characteristics in this application reflect the user's level of attention and preference for rights usage, including short-term interaction behavior characteristics and long-term interaction behavior characteristics. The short-term interaction behavior characteristics describe the user's recent operation frequency and activity level in the service scenario, while the long-term interaction behavior characteristics describe the user's operation trends and stable preferences over a longer period; the rights usage characteristics in this application refer to the user's behavioral patterns and usage rules for rights usage in a specific service scenario; and the rights preference characteristics in this application refer to the user's preference for and selection tendency for different rights in a specific service scenario.

[0052] In practice, the system first establishes a service context scenario tagging system in Excel, such as shopping check-in scenario, member check-in scenario, and fresh food consumption scenario, and assigns a unique identifier (ID) to each tag for subsequent scenario matching. Then, the system uses Python's pandas library to read benefit usage logs containing fields such as user ID, benefit ID, operation time, and page ID. By determining the correspondence between the page ID and the preset scenario tags, each benefit usage record is assigned to the corresponding scenario. After completing the scenario segmentation, the system uses Structured Query Language (SCL). The system uses SQL queries to statistically analyze core metrics for each scenario. This includes calculating the frequency of benefit usage by grouping users by user ID and scenario tag, determining usage duration by calculating the time difference between redemption and redemption times, and generating a call sequence by sorting operation times. This yields the characteristics of user benefit usage behavior in each scenario. Simultaneously, the system groups and aggregates consumption records, statistically analyzing consumption amount, consumption cycle, and interaction behavior characteristics by user ID and scenario tag. Consumption amount can be obtained by averaging or summing; consumption cycle is calculated by dividing the time difference between the earliest and latest consumption times by the number of consumptions; and interaction behavior characteristics are obtained by counting clicks and average dwell time, with time filtering to distinguish between short-term and long-term features. Finally, the system uses user ID and scenario tag as the association key to link benefit usage behavior characteristics with consumption behavior characteristics. This can be achieved through SQL inner joins or Excel lookup functions, generating a complete feature table. The system then extracts benefit usage characteristics and benefit preference characteristics for each service context scenario, saving the results as a CSV file or Excel spreadsheet. This provides a data foundation for subsequent intelligent automatic configuration of member benefits.

[0053] In step 103, based on the rights usage characteristics and the rights preference characteristics, evidence of the target member user's rights preference in each service context is determined.

[0054] In this embodiment, based on the rights usage characteristics and rights preference characteristics, evidence of the target member user's rights preference in various service contexts is determined, with reference to... Figure 2 The diagram is a flowchart illustrating the process of determining evidence of equity preference in some embodiments of this application. In this embodiment, determining evidence of equity preference can be achieved through the following steps:

[0055] In step 1031, the rights usage characteristics and rights preference characteristics under each service context are weighted and fused according to multiple dimensions to obtain an initial preference score;

[0056] In step 1032, the initial preference score is adjusted by a preset time decay function based on the usage frequency of each benefit item in different time periods to reflect the dynamic impact of recent behavior on preference judgment.

[0057] In step 1033, the adjusted preference score is dynamically corrected based on the real-time attributes of the current service context scenario to generate evidence of the target member user's rights and interests in each service context scenario.

[0058] It should be noted that the evidence of rights preference in this application refers to data reflecting the degree of user preference for various rights in a specific service scenario.

[0059] In specific implementation, the initial preference score is obtained by weighting and fusing the rights usage characteristics and rights preference characteristics under each service context scenario in multiple dimensions. This can be achieved as follows: First, the rights usage characteristics and rights preference characteristics under each service context scenario are obtained. These characteristics include rights call frequency, usage duration, call sequence, consumption amount, consumption cycle, and interaction behavior characteristics, etc. Then, the system assigns preset weights to each dimension of the characteristics. The weights can be determined based on the importance of the characteristics or the results of historical behavior data analysis. Specifically, the correlation between each characteristic and the user's actual rights selection is calculated through statistical analysis methods, and characteristics with high correlation are assigned greater weights. For long-term stable characteristics, such as long-term interaction behavior or... The system appropriately increases the weight of average spending and appropriately decreases the weight of short-term abnormal or volatile characteristics. Finally, all weights are normalized to ensure that the initial preference score obtained from the weighted fusion calculation accurately reflects the user's comprehensive preference in each service context. Further, each feature value is multiplied by its corresponding weight using a linear weighting method or a weighted average function, and then summed to obtain the comprehensive score of each benefit item in that scenario. During the fusion calculation process, the system normalizes or standardizes the feature values ​​and adjusts outliers or missing values ​​using mean imputation or interpolation methods to ensure the accuracy of the calculation results. Finally, the system uses the weighted comprehensive score of each benefit item in that service context as the initial preference score. This reflects the user's overall preference for various benefits in this scenario. The adjusted preference score is dynamically corrected based on the real-time attributes of the current service context, generating evidence of the target member's benefit preferences in each service context. This can be achieved in the following way: The system first obtains real-time attribute data of the current service context, including current time, holiday information, promotional activity status, user's geographical location, and online activity status. This can be achieved through application programming interfaces (APIs), real-time database queries, or message queues. Then, the system processes the dynamically updated initial preference score for each benefit item against the real-time attributes. This can be implemented using Python conditional statements or a rule engine, for example, during holidays or promotional activities... During the activity period, the scores of corresponding benefit items are increased by a preset ratio. Benefit items available at the user's current geographical location are given more weight, and the impact of recent interactive behaviors is enhanced during the user's active period. The system uses a linear weighting or exponential weighting method to apply real-time attributes to the initial preference score, and calculates the corrected preference score for each benefit item in the current service context. Finally, the corrected preference scores are integrated into a benefit preference evidence table or data structure for target member users in this scenario. Each record contains the user ID, scenario tag, and corrected preference score for each benefit item, which is used for subsequent priority configuration of benefits and recommendations. The corrected preference scores are used as the basis for generating benefit preference evidence.

[0060] Preferably, in this embodiment, adjusting the initial preference score based on the usage frequency of each benefit item at different time periods using a preset time decay function to reflect the dynamic impact of recent behavior on preference judgment can be achieved through the following steps:

[0061] Set a baseline decay coefficient and a time decay gradient, where the baseline decay coefficient corresponds to the reference validity of the most recent usage behavior, and the time decay gradient represents the decrease in the impact of usage behavior on the initial preference score as the time interval increases;

[0062] Calculate the time difference between the usage behavior of each right item and the current time, and reduce the benchmark decay coefficient according to the time difference and the time decay gradient to obtain the time decay factor of the behavior;

[0063] The time decay factor of the usage behavior of the rights and interests in each time period is applied to the adjustment of the initial preference score to obtain the dynamically updated initial preference score.

[0064] It should be noted that the baseline decay coefficient in this application is a coefficient that reflects the influence of recent behavior; the time decay gradient in this application is an indicator that describes the rate at which the influence of behavior on preferences decreases over time; and the time decay factor in this application refers to a coefficient used to adjust the initial preference score to reflect the time decay of behavior.

[0065] In practice, the baseline decay coefficient and time decay gradient can be set as follows: The system first sets a baseline decay coefficient and a time decay gradient for each benefit item. The baseline decay coefficient represents the reference validity of the most recent usage behavior for preference judgment. The specific setting can be based on statistical analysis of historical behavior data. For example, by calculating the ratio of the user's usage frequency of the benefit item to the number of successful redemptions in a recent period, the ratio is mapped to a value between 0 and 1 as the baseline decay coefficient to quantify the importance of recent behavior. The time decay gradient represents the decreasing impact of the usage behavior on the initial preference score as the time interval between the current and the current usage time increases. This can be achieved by analyzing user data over several past time periods. The system uses regression analysis or empirical settings to assess the impact of usage behaviors, defining the decrease in preference score for each unit increase in time interval as the time decay gradient. The system can store the baseline decay coefficient and time decay gradient as database fields or Python constants, and call them when calculating the time decay factor to dynamically adjust the contribution of each usage behavior. The baseline decay coefficient and time decay gradient serve as the basis for time decay processing. The system calculates the time difference between each benefit usage behavior and the current time, and decreases the baseline decay coefficient based on the time difference and time decay gradient to obtain the time decay factor for that behavior. This can be achieved in the following way: The system first calculates the time decay factor for each benefit usage behavior. The time difference between the current time and the current time can be obtained by subtracting the operation timestamp of the action from the current timestamp. The time difference is expressed in days or hours, representing the length of time since the action. The system then calculates the time decay factor of the action by decreasing the baseline decay coefficient based on the time difference and a preset time decay gradient. A linear decay formula can be used, for example, subtracting the product of the time decay gradient and the time difference from the baseline decay coefficient, or an exponential decay formula can be used, for example, multiplying the baseline decay coefficient by the product of the negative time decay gradient with a natural exponential rate and the time difference. The time decay factor of the use of rights items within each time period is applied to adjust the initial preference score to obtain the dynamically updated initial preference score, which can be done in the following way. Implementation: The system first matches the time decay factor of each benefit usage behavior within each time period with the initial preference score of the corresponding benefit item, establishing a correspondence through user ID and benefit ID. Then, the system performs a weighted adjustment on the initial preference score, which can be achieved by multiplying the time decay factor of each usage behavior by the initial preference score and summing the results, or by summing all behaviors using a weighted average method to generate a dynamically updated initial preference score for each benefit item in the service context. This calculation can be implemented through batch operations using Python's DataFrame, calculated fields in SQL, or weighted summation formulas in Excel, ensuring that the corresponding time decay factor is applied to each behavior.Finally, the system integrates the weighted results of all rights and benefits items to form a complete, dynamically updated initial preference score table. This dynamically updated initial preference score serves as the data basis for subsequent analysis and is used as the updated value for the user preference score.

[0066] It should be noted that this embodiment introduces a time decay function based on the usage frequency of each benefit item in different time periods to dynamically adjust the initial preference score. Compared with the existing technology, which usually only evaluates preferences based on static cumulative usage behavior, this can solve the technical problems that preference judgment cannot reflect recent behavior changes and that the influence of historical behavior is too great, leading to lag or inaccuracy in preference prediction. Specifically, by setting a benchmark decay coefficient to quantify the effectiveness of recent behavior and combining it with the time decay gradient to calculate the time decay factor, the dynamic adjustment of behavior in different time periods is applied to the initial preference score. This gives recent usage behavior a higher weight in preference judgment, while the influence of older historical behavior decreases. This achieves dynamic updating and real-time reflection of preference evaluation, improves the accuracy and agility of user preference analysis, and significantly enhances the system's adaptability and accuracy in identifying user benefit preferences in multiple time periods and scenarios. This demonstrates the creativity of the technical solution in dynamic preference modeling.

[0067] In step 104, based on the evidence of rights and interests in each service context, the priority configuration rights and interests items of the target member user are determined, and then the priority configuration rights and interests items are used as the recommended rights and interests configuration results of the target member user.

[0068] In this embodiment, determining the preferred privileges of the target member user based on privilege preference evidence in each service context can be achieved through the following steps:

[0069] The contribution coefficient of each benefit item to the benefit scenario is determined based on the benefit preference evidence in each service context.

[0070] By integrating the benefit scenario contribution coefficients of all service context scenarios, the benefit priority of each benefit item is obtained to reflect the target member users' preference for different benefit items;

[0071] All candidate benefits are sorted according to the benefit priority, and the benefit items with the highest ranking are selected as the priority benefit items for the target member user.

[0072] It should be noted that the benefit scenario contribution coefficient in this application is an indicator that measures the degree of contribution of a benefit item to user preference in a specific service scenario; the benefit priority in this application is an indicator that measures the overall preference importance of a certain benefit item; and the priority allocation benefit item in this application refers to the high-preference benefit that the system prioritizes allocating to users.

[0073] In specific implementation, determining the benefit scenario contribution coefficient of each benefit item based on benefit preference evidence under each service context scenario can be achieved as follows: First, obtain the benefit preference evidence table for each service context scenario, including user ID, scenario label, and preference score of each benefit item. Then, normalize the preference scores of all benefit items in each scenario. This can be calculated by dividing the preference score of a certain benefit item by the sum of the preference scores of all benefit items in that scenario, thereby quantifying the relative contribution of that benefit item in that scenario. This step can be implemented using the pandas library in Python, grouped by "user ID + scenario label" and then vectorized. The normalization result of each benefit item generates its corresponding benefit scenario contribution coefficient. The benefit priority of each benefit item can be obtained by integrating the benefit scenario contribution coefficients of all service context scenarios as follows: Integrate the benefit scenario contribution coefficients calculated under each service context scenario to obtain the comprehensive benefit priority of each benefit item. The integration method can be a weighted sum or an arithmetic average. For example, for each benefit item, its weights under different scenarios can be adjusted. The contribution coefficient of each benefit scenario is multiplied by the weight of the corresponding scenario, and the weighted results are summed to obtain the comprehensive score. The weights can be set according to the importance of the scenario, the user's historical usage frequency, or business strategy. This calculation can be implemented by grouping by "user ID + benefit ID" in the pandas library of Python and then performing vectorized weighted summation. After integration, each benefit item corresponds to a comprehensive value. The higher the value, the greater the comprehensive contribution of the benefit item to user preference in the overall service scenario. This comprehensive value is used as the benefit priority. The comprehensive value is used as the benefit priority of each benefit item. According to the benefit priority, all candidate benefit items are sorted, and the benefit items with the highest ranking are selected as the priority benefit items for the target member user. This can be implemented in the following way: the system sorts all candidate benefit items in descending order according to the benefit priority, and selects several benefit items with the highest ranking as the priority benefit items for the target member user. The ranking result and the output of the selection step are used as the final priority benefit items for the system to recommend or automatically configure in the future. The benefit items with the highest ranking are used as the priority benefit items for the target member user.

[0074] It should be noted that, in this application, using the priority configuration rights as the recommended rights configuration result for the target member user means using the selected high-priority rights to provide personalized recommendations or automatic allocation to the user.

[0075] In summary, this application constructs multi-dimensional rights usage characteristics and preference characteristics by obtaining members' rights usage records and consumption behavior records, and generates rights preference evidence in various service contexts, thereby achieving a quantitative description of users' personalized preferences. Since the rights preference evidence considers key indicators such as usage frequency, usage duration, consumption amount, consumption cycle, and interaction behavior, it can accurately reflect users' actual preferences in different scenarios. The priority rights items determined based on this preference evidence, after sorting and weighted integration, can reflect users' comprehensive preferences for each rights item, thus ensuring that recommended or automatically allocated rights are highly matched with user needs. This solution transforms user behavior data into quantifiable preference indicators, which are then used to determine priority rights, enabling the recommendation results to improve user rights usage and satisfaction, while reducing the allocation of non-target rights and resource waste, achieving intelligent and dynamic management of member rights configuration.

[0076] Furthermore, in another aspect of this application, in some embodiments, this application provides an intelligent automatic configuration device for a membership benefits scheme. This intelligent automatic configuration device for a membership benefits scheme includes a membership benefits intelligent configuration unit, as referenced. Figure 3 The figure is a schematic diagram of the structure of a smart configuration unit for membership benefits according to some embodiments of this application. The smart configuration unit for membership benefits includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below:

[0077] The acquisition module 201 in this application is mainly used to obtain the target member user's rights usage records and consumption behavior records in the platform from the user database in response to the member rights configuration requirements.

[0078] Processing module 202, in this application, is used to extract the rights usage characteristics and rights preference characteristics of the target member user in different service contexts based on the rights usage record and the consumption behavior record;

[0079] It should be noted that the processing module 202 is also used to determine the evidence of the target member user's rights preference in each service context based on the rights usage characteristics and the rights preference characteristics;

[0080] The execution module 203 in this application is mainly used to determine the priority configuration rights items of the target member user based on the rights preference evidence in each service context scenario, and then use the priority configuration rights items as the recommended rights configuration result of the target member user.

[0081] The foregoing has detailed examples of an intelligent automatic configuration method and apparatus for a membership benefits scheme provided in this application. It is understood that, to achieve the aforementioned functions, the apparatus includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0082] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described intelligent automatic configuration method for the membership benefits scheme.

[0083] In some embodiments, reference Figure 4 The dashed lines in the figure indicate that the unit or module is optional. This figure is a structural schematic diagram of a computer device for implementing an intelligent automatic configuration method for membership benefits schemes according to embodiments of this application. The intelligent automatic configuration method for membership benefits schemes described in the above embodiments can be achieved through… Figure 4 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device may be a terminal device, a server or a chip.

[0084] Processor 301 can be a general-purpose processor or a special-purpose processor. For example, processor 301 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 305 for inputting (receiving) and outputting (transmitting) signals.

[0085] For example, the computer device may be a chip, and the communication unit 305 may be the input and / or output circuit of the chip, or the communication unit 305 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0086] For example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0087] The computer device may include one or more memories 302 storing a program 304. The program 304 can be executed by a processor 301 to generate instructions 303, causing the processor 301 to execute the method described in the above method embodiments according to the instructions 303. Optionally, the memory 302 may also store data (such as a target audit model). Optionally, the processor 301 may also read data stored in the memory 302, which may be stored at the same storage address as the program 304, or it may be stored at a different storage address than the program 304.

[0088] The processor 301 and memory 302 can be configured separately or integrated together, for example, integrated on the system on chip (SOC) of the terminal device.

[0089] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0090] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described intelligent automatic configuration method for the membership benefits scheme.

[0092] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0093] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for intelligent automatic configuration of membership benefits schemes, characterized in that, Includes the following steps: In response to the needs of configuring membership benefits, the system retrieves the usage records and consumption behavior records of target members on the platform from the user database. Based on the rights usage records and the consumption behavior records, the rights usage characteristics and rights preference characteristics of the target member users in different service context scenarios are extracted. The service context scenario refers to the specific service type and operating environment corresponding to the user's use of rights or consumption behavior on the platform. Based on the rights usage characteristics and rights preference characteristics, evidence of the target member user's rights preference in each service context is determined; Based on the evidence of rights and interests in each service context, the priority rights and interests of the target member user are determined, and then the priority rights and interests are used as the recommended rights and interests configuration result of the target member user. Specifically, determining the evidence of the target member user's rights preference in various service contexts based on the rights usage characteristics and rights preference characteristics includes: The rights usage characteristics and rights preference characteristics under each service context are weighted and fused according to multiple dimensions to obtain an initial preference score; Based on the usage frequency of each benefit item in different time periods, the initial preference score is adjusted by a preset time decay function to reflect the dynamic impact of recent behavior on preference judgment; The adjusted preference score is dynamically corrected based on the real-time attributes of the current service context, generating evidence of the target member user's rights and interests in each service context. Specifically, the initial preference score is adjusted using a preset time decay function based on the usage frequency of each benefit item over different time periods to reflect the dynamic impact of recent behavior on preference judgment. Set a baseline decay coefficient and a time decay gradient, where the baseline decay coefficient corresponds to the reference validity of the most recent usage behavior, and the time decay gradient represents the decrease in the impact of usage behavior on the initial preference score as the time interval increases; Calculate the time difference between the usage behavior of each right item and the current time, and reduce the benchmark decay coefficient according to the time difference and the time decay gradient to obtain the time decay factor of the behavior; The time decay factor of the usage behavior of the rights and interests in each time period is applied to the adjustment of the initial preference score to obtain the dynamically updated initial preference score; Specifically, the time decay factor of the usage behavior of the benefit items within each time period is applied to the adjustment of the initial preference score to obtain the dynamically updated initial preference score. This is achieved in the following way: First, the time decay factor of each benefit usage behavior within each time period is matched with the initial preference score of the corresponding benefit item. The matching establishes a correspondence through user ID and benefit ID. The initial preference score is then adjusted by weighting the adjustment by multiplying the time decay factor of each usage behavior by the initial preference score and then summing them up, or by summing all behaviors using a weighted average method, to generate the dynamically updated initial preference score of each benefit item in the service context.

2. The method as described in claim 1, characterized in that, Based on the aforementioned rights usage records and consumption behavior records, extracting the rights usage characteristics and rights preference characteristics of the target member user in different service contexts specifically includes: The rights usage records are segmented by scenario tags to obtain the rights call frequency, usage duration and call sequence under each service context scenario; The consumption behavior records are aggregated to obtain consumption amount, consumption cycle and interaction behavior features corresponding to each service context scenario; By associating the frequency of rights calls, usage duration, and call sequence with the consumption amount, consumption cycle, and interaction behavior characteristics, the rights usage characteristics and rights preference characteristics of the target member users are extracted.

3. The method as described in claim 2, characterized in that, The interactive behavior characteristics include short-term interactive behavior characteristics and long-term interactive behavior characteristics.

4. The method as described in claim 1, characterized in that, Based on evidence of benefit preferences in various service contexts, the specific priority benefit items for the target member user are determined to include: The contribution coefficient of each benefit item to the benefit scenario is determined based on the benefit preference evidence in each service context. By integrating the benefit scenario contribution coefficients of all service context scenarios, the benefit priority of each benefit item is obtained to reflect the target member users' preference for different benefit items; All candidate benefits are sorted according to the benefit priority, and the benefit items with the highest ranking are selected as the priority benefit items for the target member user.

5. The method as described in claim 1, characterized in that, The records of rights usage include data on users' claims, cancellations, and expiration of rights.

6. An intelligent automatic configuration device for membership benefits schemes, the device comprising an intelligent configuration unit for membership benefits, which performs intelligent automatic configuration of membership benefits schemes using the method described in any one of claims 1 to 5, characterized in that, The intelligent configuration unit for membership benefits includes: The acquisition module is used to retrieve the target member's rights usage records and consumption behavior records on the platform from the user database in response to the member rights configuration requirements; The processing module is used to extract the benefit usage characteristics and benefit preference characteristics of the target member user in different service contexts based on the benefit usage record and the consumption behavior record; The processing module is further configured to determine the evidence of the target member user's rights preference in each service context based on the rights usage characteristics and the rights preference characteristics; The execution module is used to determine the priority configuration rights of the target member user based on the rights preference evidence in each service context scenario, and then use the priority configuration rights as the recommended rights configuration result of the target member user.

7. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to retrieve the code and execute the intelligent automatic configuration method for the membership benefits scheme as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent automatic configuration method of the membership benefits scheme as described in any one of claims 1 to 5.

Images