User activeness improving method and system based on point shopping mall

Abstract

The invention discloses a user activeness improvement method and system based on a point shopping mall, and mainly relates to the technical field of electronic commerce operation. Comprising the following steps: collecting basic behavior data of a user in a point shopping mall; calculating a real-time integral value of the user according to a preset behavior type and integral weight mapping relation; constructing a user portrait based on the user historical behavior data; generating a personalized task pool according to the user portrait; when the user triggers a task participation condition, pushing a task list in the personalized task pool to the user; setting a social interaction scene in the point shopping mall; establishing a cross-platform point intercommunication mechanism, and allowing the user to exchange points of other platforms into general points of a point shopping mall according to a preset exchange rate; and dynamically adjusting an integral acquisition rule and a commodity exchange threshold according to the user integral value and the activeness level. The method has the beneficial effects that the operation effect of the point shopping mall is optimized while the user activeness is improved and the stickiness is enhanced.

Description

Technical Field

[0001] This invention relates to the field of e-commerce operation technology, specifically a method and system for improving user activity based on an points mall. Background Technology

[0002] With the popularization of e-commerce and digital operations, points malls have become an important tool for various platforms to enhance user stickiness and promote consumption conversion. Currently, most companies incentivize user participation by setting basic points rules (such as points for purchases and task rewards) and product redemption systems, but user activity generally faces problems such as short bottleneck periods and low repurchase rates. Some advanced platforms have tried to introduce personalized recommendation technology and social interaction mechanisms, but they still suffer from limitations such as rigid points rules, homogenized task designs, and insufficient cross-platform collaboration, making it difficult to achieve a sustained increase in user activity.

[0003] The core problem with existing technologies is: 1. The fixed points calculation rules do not take into account the dynamic changes in user activity, resulting in insufficient incentives for highly active users and excessively high barriers to participation for inactive users. 2. The task design lacks personalization and fails to accurately match the consumption preferences and behavioral habits of different users, thus reducing users' willingness to participate; 3. The points system operates in a closed system with poor interoperability with the external ecosystem, which limits the use cases and value conversion of points.

[0004] The root cause of these problems lies in the fact that existing technologies have not established a dynamic points management mechanism based on user profiles, making it difficult to adjust incentive strategies in real time based on user behavior data. Furthermore, the lack of cross-platform data integration and collaborative operation capabilities prevents the formation of a synergistic ecosystem to enhance user activity. In addition, the task design model of traditional points malls fails to fully leverage the dissemination value of social networks, resulting in limited incentive effects on user interaction.

[0005] Therefore, there is an urgent need for a method and system to improve user activity based on an points mall to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for improving user activity based on an points mall, which optimizes the operation of the points mall while increasing user activity and stickiness.

[0007] To achieve the above objectives, the present invention employs the following technical solution: On the one hand, the present invention provides a method for improving user activity based on an points mall, including the following steps: Step S1: Collect basic behavioral data of users in the points mall, including: login frequency, product browsing history, points acquisition and consumption history; Step S2: Calculate the user's real-time points value according to the preset mapping relationship between behavior type and points weight, wherein the points weight is dynamically adjusted according to the user's activity level; Step S3: Construct a user profile based on the user's historical behavior data. The user profile includes: consumption preferences, points usage habits, and activity cycle characteristics. Step S4: Generate a personalized task pool based on the user profile in step S3. The personalized task pool includes: basic tasks, advanced tasks, and social fission tasks. Step S5: When the user triggers the task participation conditions, push the task list from the personalized task pool in step S4 to the user, and update the points value in real time according to the task completion status. Step S6: Set up social interaction scenarios in the points mall, where users can earn extra points by inviting friends, forming teams to complete tasks, or participating in topic discussions; Step S7: Establish a cross-platform points exchange mechanism, allowing users to exchange points from other platforms for universal points in the points mall at a preset exchange rate; Step S8: Dynamically adjust the points acquisition rules and product redemption thresholds based on user points and activity level.

[0008] Preferably, in step S2, the dynamic adjustment of the integral weight includes: When a user's activity level increases, the weight of points for high-frequency behaviors is increased, while the weight of points for low-frequency behaviors is decreased. When a user's activity level decreases, the weight of high-frequency behaviors in the score is reduced, while the weight of low-frequency behaviors in the score is increased.

[0009] Preferably, in step S4, the generation of the personalized task pool includes: The basic tasks are low-difficulty tasks, including daily login and product reviews, which will earn a fixed number of points upon completion. Advanced tasks are medium to high difficulty tasks, including: cumulative spending and consecutive check-ins. Upon completion, you can get tiered point rewards. Social referral tasks are socially oriented tasks, which include: inviting friends to register and forming teams to take on challenges. Upon completion, users can earn dynamic points rewards, which are linked to the activity level of the invited users.

[0010] Preferably, in step S6, the social interaction scenario includes: Establish a social network for users, allowing them to view their friends' points rankings, task completion progress, and redemption records; Design team tasks where users need to team up with at least one friend to complete the task. Upon completion, all team members will receive bonus points. A dedicated discussion area is set up where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a certain threshold, a points-doubling reward is triggered.

[0011] Preferably, in step S7, the cross-platform points interoperability mechanism includes: Establish interface protocols with external platforms to obtain users' points data on those platforms; An exchange rate mapping table is established based on the points type of the external platform and the general points in the points mall. The exchange rate mapping table is dynamically updated based on the user activity and points value of the external platform. After a user submits a redemption request, the system automatically verifies the redemption eligibility and completes the points conversion. The converted general points can be used for all redemption scenarios within the points mall.

[0012] Preferably, in step S8, the dynamic adjustment of the points acquisition rules and the product redemption threshold includes: When a user's points exceed a preset threshold, the redemption threshold for high-value goods is increased, while the redemption threshold for low-value goods is decreased. When a user's activity level decreases, increase the point rewards for basic tasks and reduce the point consumption for advanced tasks. We adjust the point weighting and task difficulty coefficient of behaviors in real time based on marketing activities and user feedback.

[0013] On the other hand, the present invention also provides a system for implementing the above-described method for improving user activity based on an points mall, the system comprising: The data collection module is configured to collect basic behavioral data of users within the points mall; The points calculation module is configured to calculate the user's real-time points value based on the preset mapping relationship between behavior type and points weight, and dynamically adjust the points weight according to the user's activity level. The user profile building module is configured to build user profiles based on users' historical behavior data, including consumption preferences, points usage habits, and activity cycle characteristics. The task generation module is configured to generate a personalized task pool that includes basic tasks, advanced tasks, and social sharing tasks based on user profiles. The task push module is configured to push a list of tasks when the user triggers the conditions for participating in a task, and update the points value according to the task completion status. The social interaction module is configured to set up social interaction scenarios within the points mall, allowing users to earn extra points rewards through social behaviors. The cross-platform interoperability module is configured to establish a cross-platform points interoperability mechanism, allowing users to redeem points from other platforms; The strategy optimization module is configured to dynamically adjust the points rules and operational strategies based on user points, activity levels, and feedback.

[0014] Preferably, the integral calculation module includes: The weight adjustment submodule is configured to increase the weight of high-frequency behaviors and decrease the weight of low-frequency behaviors when the user's activity level increases; and decrease the weight of high-frequency behaviors and increase the weight of low-frequency behaviors when the user's activity level decreases. The real-time calculation submodule is configured to dynamically update user points based on real-time user behavior data and adjusted point weights.

[0015] Preferably, the social interaction module includes: The relationship network submodule is configured to establish a user's social relationship network, displaying friends' point rankings, task progress, and redemption records; The team task submodule is configured to design team tasks, where users need to team up with friends to complete tasks and earn bonus points. The content incentive submodule is configured to set up a topic discussion area where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a threshold, a points doubling reward is triggered.

[0016] Preferably, the cross-platform interoperability module includes: The interface protocol submodule is configured to establish an interface protocol with an external platform to obtain the user's points data on the external platform; The exchange rate mapping submodule is configured to dynamically update the exchange rate mapping table based on user activity and points value on external platforms. The redemption processing submodule is configured to verify the user's redemption eligibility and complete the points conversion. The converted general points can be used for all redemption scenarios in the points mall.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Dynamically Activate User Engagement: By dynamically adjusting the weight of points based on user activity levels, the system solves the problems of insufficient incentives for highly active users and excessively high barriers to participation for inactive users caused by fixed point rules. When user activity changes, the system automatically optimizes the rules for acquiring and redeeming points, which incentivizes highly active users to maintain their activity frequency while reducing the participation barriers for inactive users, forming a positive cycle of "activity-points-behavior" and effectively improving users' continued engagement.

[0018] 2. Accurately improve task completion efficiency: Based on user profiles, a personalized task pool is generated, upgrading general tasks into differentiated tasks that match users' consumption preferences and points usage habits. This solves the problem of low user interest and poor completion rate caused by homogeneous task design in existing technologies. Basic tasks ensure the universality of users' daily participation, advanced tasks meet the challenging needs of highly active users, and social fission tasks expand the scope of participation by utilizing users' social relationship chains, significantly improving the accuracy of task reach and user acceptance.

[0019] 3. Expanding the Value and Ecosystem Boundaries of Points: By setting up social interaction scenarios and establishing a cross-platform points interoperability mechanism, the closed nature and limited usage scenarios of the traditional points system are broken. Social interaction binds points acquisition with social behavior, which not only enhances user stickiness and a sense of belonging to the platform, but also expands the user base through a viral effect; cross-platform points interoperability gives points the ability to circulate across scenarios, enhances the perceived actual value of points, solves the pain point of limited value of points on a single platform, and further enhances users' dependence on the points mall. Attached Figure Description

[0020] Figure 1 This is a flowchart of the method for improving user activity based on an points mall according to the present invention; Figure 2 This is a schematic diagram of the user activity enhancement system based on the points mall of the present invention. Detailed Implementation

[0021] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined in this application.

[0022] like Figure 1 As shown, this embodiment provides a method for improving user activity based on an points mall, including the following steps: Step S1: Collect basic behavioral data of users in the points mall. Basic behavioral data includes login frequency, product browsing history, and points acquisition and consumption history. Step S2: Calculate the user's real-time points value according to the preset mapping relationship between behavior type and points weight. The points weight is dynamically adjusted according to the user's activity level. The dynamic adjustment of points weight includes: when the user's activity level increases, the points weight of high-frequency behaviors is increased and the points weight of low-frequency behaviors is decreased; when the user's activity level decreases, the points weight of high-frequency behaviors is decreased and the points weight of low-frequency behaviors is increased. Step S3: Construct user profiles based on users' historical behavior data. User profiles include consumption preferences, points usage habits, and activity cycle characteristics. Step S4: Generate a personalized task pool based on the user profile. The personalized task pool includes basic tasks, advanced tasks, and social sharing tasks. The method for generating the personalized task pool includes: Basic tasks include low-difficulty tasks such as daily login and product reviews, and you can earn a fixed number of points upon completion. Advanced tasks include medium-to-high difficulty tasks such as cumulative spending and consecutive check-ins, and you can get tiered points rewards upon completion. Social referral tasks include socially oriented tasks such as inviting friends to register and team challenges. Upon completion, dynamic points rewards can be obtained, which are linked to the activity level of the invited users. Step S5: When the user triggers the task participation conditions, push the task list in the personalized task pool to the user, and update the points value in real time according to the task completion status. Step S6: Set up social interaction scenarios within the points mall. Users can earn extra points by inviting friends, forming teams to complete tasks, or participating in topic discussions. Social interaction scenarios include: Establish a social network for users, allowing them to view their friends' points rankings, task completion progress, and redemption records; Design team tasks where users need to team up with at least one friend to complete the task. Upon completion, all team members will receive bonus points. A dedicated discussion area is set up where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a certain threshold, a double points reward is triggered. Step S7: Establish a cross-platform points exchange mechanism, allowing users to exchange points from other platforms for universal points in the points mall at a preset exchange rate; Step S8: Dynamically adjust the points acquisition rules and product redemption thresholds based on user points and activity level.

[0023] In this embodiment, we take the "points mall" of an e-commerce platform as an example: Specifically, step S1 is implemented as follows: 1. Login frequency data collection: The system records the timestamp of each user's login to the mall, the login channel (APP, web page, mini program), the duration of a single login, the number of consecutive login days, and the weekly login frequency distribution (such as the difference between the number of logins on weekdays and weekends) in real time, and automatically calculates the total number of logins and the average login interval for the month. 2. Product browsing history collection: When a user browses a product, the backend captures the product ID, category (such as digital products, home furnishings, virtual services, etc.), browsing order, duration of stay on a single product page, whether the product details page is triggered to view parameters / reviews, whether it is added to the favorites or comparison list, and whether the user is redirected to the product redemption rules page after browsing. 3. Collection of Points Acquisition and Consumption Records: For points acquisition, the system records the triggering behavior for each point increase (such as points back on purchases, completing check-in tasks, and rewards for reviewing and sharing reviews), the time of occurrence of the corresponding behavior, the number of points acquired, and the validity period of the points; for points consumption, the system records the ID of the redeemed item, the redemption time, the number of points consumed, whether a combination of points and cash was used for payment, and the number and time of expired unused points. All data is synchronized to the user behavior database in real time and generates traceable behavior logs.

[0024] In step S2, the user's real-time points value Using a weighted summation model, the calculation formula is as follows: ; in, This is a timestamp, representing the current calculation time. The total number of behavior types (such as login, browsing, consumption, sharing, etc.); For the first The basic score weights for each type of behavior (initial values ​​are set by the operational strategy); Indicates that the user is The first time triggered The quantitative value of a behavior (e.g., 1 login is counted as 1, and the amount of consumption is counted as the actual amount / 100). Indicates the first The dynamic adjustment factor for this behavior (determined by the activity level); User Activity Level Calculations are based on historical behavioral data, using a piecewise function: ; in: The user's activity score at time t is calculated using the following formula: ; in, , , , Normalized weighting coefficients ( Each indicator was standardized using Z-score. , , These are the thresholds for classifying activity levels; Dynamic integral weight adjustment methods include: 1. Classification of high-frequency and low-frequency behaviors: Based on users' historical behavior data, the system uses the K-means clustering algorithm to classify behaviors into high-frequency behaviors (such as daily login and browsing products) and low-frequency behaviors (such as inviting friends and large-scale purchases). The classification criteria are as follows: ; 2. Formula for dynamic adjustment of integral weights: When user activity level When changes occur, the basic weights Adjust to dynamic weights : ; in: The activity level for the previous calculation period; This is an adjustment factor (e.g., 0.1, meaning the weight adjustment is 10% each time the level changes). Represents a symbolic function. When it is 1, The time is -1. The time is 0; This is a behavior type factor, with 1 for high-frequency behaviors and -1 for low-frequency behaviors. Assuming user activity level starts from Upgraded to The base weight of a high-frequency behavior (such as logging in). The adjusted weights are: ; Meanwhile, the base weight of a low-frequency behavior (such as inviting friends) The adjusted version is as follows: ; The specific implementation scenario of the "points mall" in this embodiment is as follows: 1. Incentives for highly active users: When a user logs in for 7 consecutive days and completes 5 product redemptions (activity level increases from 3 to 4): the point weight for the high-frequency behavior "daily login" increases from 5 points / time to 6 points / time; the point weight for the low-frequency behavior "invite friends" decreases from 20 points / time to 16 points / time; a new advanced task of "sign in for 7 consecutive days" is added, which will reward an additional 30 points upon completion (originally only 10 points). 2. Recalling inactive users: When a user has not logged in for 14 consecutive days (activity level drops from 2 to 1): the point weight for the high-frequency behavior "login" increases from 5 points / time to 8 points / time; the point weight for the low-frequency behavior "sharing products" increases from 15 points / time to 25 points / time; a personalized task of "login to receive 50 points" is pushed to lower the threshold for user return.

[0025] The implementation of step S3 specifically includes the following steps: 1. Vectorize consumer preference characteristics: This is used to describe a user's preference for product categories within the points mall, and the calculation formula is as follows: ; in, For users to choose product categories Preference level (value range 0-1, higher value means stronger preference); For category The total number of items included; Indicates user preference for product categories The Middle The behavioral quantification value of each item (viewing record 1, adding to favorites record 2, adding to redemption list record 3, completing redemption record 5); In step S2, the first The point weighting of each product's corresponding behavior (e.g., browsing behavior has a weight of 0.3, and redemption behavior has a weight of 1.0). Indicates the number of days between the time the action occurred and the current time (unit: days); This represents the time decay coefficient (a fixed value of 30, meaning that only the behavioral data of the most recent 30 days is retained to enhance timeliness). : Indicates the commodity value coefficient (set according to the points required to redeem the commodity; 1.2 for high-point commodities, 1.0 for medium-point commodities, and 0.8 for low-point commodities). 2. Vectorize the characteristics of habitual use of integrals: This is used to describe the frequency, preferred channels, and sensitivity of users to points consumption, and is quantified through two core metrics: (1) Frequency of points consumption (unit: times / week): ; in, Indicates the first Each point consumption behavior (1 point is awarded for complete redemption, 0 points are awarded for incomplete redemption); The statistical period is (unit: week, usually 4 weeks). Activity level weight (in step S2) The corresponding coefficients are 1.2, 1.0, 0.8, and 0.6 for levels 1-4 respectively, with lower-active users given higher weight to highlight their consumption potential. (2) Points sensitivity (reflects the user's perception of the value of points, with a value of 0-1): ; in, Indicates the first Cash equivalent value of the goods exchanged (unit: yuan); This represents the points consumed in the s-th exchange. The higher the value, the more likely the user is to redeem high-value goods with low points (high sensitivity). 3. Quantify the characteristics of the active cycle: This describes the temporal patterns of user activity, including two dimensions: time-period preference and periodic stability. (1) Time-period preference probability (the probability that a user is active during a certain time period): ; in, Indicates the user's position in the first month. The number of active users during an hourly period (e.g., 9:00-10:00) (cumulative actions such as login and browsing); : This indicates the activity weight corresponding to this time period in step S2 (the weight is increased during periods of high activity, such as 1.5 for the evening period from 20:00 to 22:00 and 0.5 for the early morning period).

[0026] (2) Periodic stability index (stability of user activity patterns, value 0-1): ; in, This refers to the number of times a user is active on each day of the week (e.g., the number of logins from Monday to Sunday). The standard deviation reflects the degree of dispersion of the active distribution; This is the mean, reflecting the average activity level; The higher the value, the more regular the user's activity time (e.g., logging in every Wednesday and Saturday). 4. Dynamic update mechanism for portrait features: User profile feature values ​​are automatically updated every day at midnight, using the following formula: ; in, For historical portrait feature values; The feature value calculated for newly added behaviors on the same day; The historical weighting factor (valued at 0.7 to ensure profile stability and avoid the impact of short-term behavioral fluctuations); when the user activity level (in step S2) is... When changes occur, Automatic adjustment (when leveling up) Accelerate the weighting of new behaviors; when the level decreases (Maintaining the stability of historical characteristics) The specific implementation scenario of the "points mall" in this embodiment is as follows: Highly active users (Level 4): Consumption preferences The display shows "Digital Products (0.82) is greater than Virtual Services (0.75)," indicating a high sensitivity to points. (Prefers to redeem high-value goods with high points), time period preference Concentrated between 20:00 and 22:00 (weight 1.5), with periodic stability. (Active 3 days a week); Low-activity users (Level 1): Consumption preferences The display shows "Home Furnishings (0.68) is greater than Food (0.62)," indicating the frequency of points consumption. Weekly / time period preference is dispersed (No obvious peak value), periodic stability (Active time is random).

[0027] The implementation of step S4 is as follows: Personalized task pools are based on the three-dimensional features of the user profile (consumption preferences) in step S3. Points usage habits / Activity cycle / This task is generated using a task matching algorithm to ensure a high degree of alignment between the task and user behavior characteristics. 1. Basic task matching model: The formula for calculating the matching degree of basic tasks (such as daily login, product reviews) is as follows: ; in, Basic task matching degree (value range 0-1, the higher the value, the higher the matching degree); , , Weighting coefficients ( , , ); This indicates the probability of a user's time period preference in step 3 (e.g., active users in the evening have a higher matching degree for "evening limited-time login tasks"). : Represents the attenuation coefficient (taken as 0.5, to control the intensity of the influence of time period preferences); 2. Advanced Task Matching Model: The matching degree calculation formula for advanced tasks (such as cumulative spending and consecutive check-ins) is as follows: ; in, Indicates the matching degree of advanced tasks; , , , Weighting coefficients ( , , , ); This indicates the user's current cumulative completion amount (e.g., having checked in for 5 consecutive days). This represents the task target value (e.g., checking in for 7 consecutive days). The attenuation coefficient for activity level is set to 0.3 to control the intensity of the influence of activity level. 3. Social fission task matching model: The matching formula for social sharing tasks (such as inviting friends or team challenges) is as follows: ; in, For social sharing and viral marketing tasks, the matching degree is high. , , Indicates the weighting coefficient ( , , ); This represents the number of active friends in the user's social network (statistics from the relationship network sub-module in step 3). Indicates the first The activity level of each friend; Total number of friends; Based on task matching degree The system automatically assigns task types and reward points, forming a tiered incentive system, including: 1. Basic Task Reward Model: Basic task points rewards The calculation formula is: ; in, The base points value (e.g., 5 points are awarded for daily login by default); This is a level adjustment coefficient (set to 0.1; for every level increase in activity level, the reward increases by 10%). 2. Advanced Task Reward Model: Advanced Task Points Rewards Using a step function: ; in: , , The reward values ​​are distributed in stages; for every 1 / 3 increase in task completion, an additional reward corresponding to that stage is added. 3. Social Reward Model for Viral Marketing Tasks: Social sharing and viral marketing task points rewards Linked to the activity level of invited users: ; in, Initial reward points (e.g., 20 points for each successful referral). The number of friends successfully invited; : for the first The activity level of each invited friend; This is the level conversion coefficient (taken as 0.5, meaning that for every level of activity the invited friend increases, the inviter receives an additional 0.5 times the base reward). The specific implementation scenario of the "points mall" in this embodiment is as follows: Highly active digital enthusiast (Level 4): System pushes "Evening Limited-Time Digital Product Review Task" (matching degree) (Reward: 20 points) and "7-Day Consecutive Day Digital Goods Redemption Task" (Matching score) (100 points as a tiered reward) Low-activity home furnishing users (Level 1): The system pushes a "Invite friends to redeem home furnishings task" (matching score) Invite one person and receive 30 points; "First completion of home furnishing product evaluation task" (matching score) (15 points will be awarded).

[0028] The implementation of step S5 is as follows: Through three core steps—trigger condition judgment, task priority ranking, and real-time points calculation—we ensure that users receive the most suitable tasks and obtain dynamic incentives. 1. Task triggering condition judgment model: When user behavior meets the following trigger functions, the system automatically pushes a task list: ; in, Indicates that the user is Behavioral feature vectors at any given moment (e.g., login record 1, browsing product record 2, redeeming product record 5); Indicates the behavioral weights (and the integral weights in step S2). Positive correlation ); This indicates the trigger threshold (dynamically adjusted based on user activity level). (The threshold for inactive users is even lower). 2. Task Priority Ranking Model: Based on the matching degree of step S4 Calculate task push priority based on the user's current state. : ; in, The task matching degree (basic task) calculated for step S4 Advanced tasks Social tasks ); Indicates the urgency of the task (1 for time-limited tasks, 0 for long-term tasks); This represents the urgency coefficient (taken as 0.5). Indicates the degree of task completion ( (If the task has not started, take 0). This represents the completion coefficient (set to 0.3 to incentivize users to complete tasks in the near term). 3. Real-time update model of integrals: Upon completion of the task, the user's points will be updated according to the following formula: ; in, This indicates the user's current points value; This indicates the task reward points (from step S4). , , ); The change in activity level after the task is completed (e.g., from) Rise to ,but ); This is the level change coefficient (taken as 0.2, with an additional 20% bonus points awarded when the level increases). This is a time multiplier (1.5 for peak hours and 0.8 for off-peak hours). 4. Real-time task status synchronization mechanism: Task status Updated in real time based on user behavior: ; in, This represents the current completed amount; The target completion amount; The deadline for the task; The specific implementation scenario of the "points mall" in this embodiment is as follows: Task triggering and push notifications based on user activity level Trigger threshold The user logged in at 20:00 ( , Browse 5 digital products () , ): The system pushes the highest priority "Evening Digital Product Review Task" (matching score 0.85, urgency 1, priority 1.275). Points are updated in real time for users who complete the above commenting tasks; basic reward applies. Points were earned during peak hours (20:00-22:00). Activity level increased from 2 to 3 ( ),but: .

[0029] The implementation of step S6 is as follows: By building a user social network and designing team tasks and content incentive mechanisms, a closed loop of "social behavior - points rewards - increased activity" is formed: 1. Social Relationship Network Construction Model: User Social Influence The calculation formula is: ; in, For the first The activity level of each friend; In order to be with the first Interaction frequency of each friend (number of interactions in the last 30 days / 30); In order to be with the first Interest similarity among friends (values ​​range from 0 to 1); Social distancing is defined as follows: 1 for direct friends, 2 for indirect friends, and so on. , , Weighting coefficients ( , , ); This is the attenuation factor (set to 0.5 to control for the impact of social distancing). 2. Team Task Points Bonus Model: Points rewards earned by individual team members upon completion of a team task. for: ; in, The basic reward for completing a task individually; This refers to the number of team members who actually participated in completing the task; The target number of players in the team; The average social influence of the team members; , Addition factor ( , ); 3. Content Incentive Points Calculation Model: Points earned by users for publishing content. for: ; When the number of likes, comments, or shares reaches a certain threshold, points are doubled: ; Final score: ; in, Points are awarded for basic content (e.g., 5 points are awarded for posting a valid comment). , , Interaction weight ( , , ); , , For threshold ( , , ); This is the activity level coefficient (set to 0.1; for each level increase, the points increase by 10%). The specific implementation of the social interaction module: 1. Matching degree of the friend recommendation algorithm in the relationship network submodule for: ; in, Based on the similarity of interests between the user and the candidate friends; The number of mutual friends; , The adjustment coefficient ( , ); 2. Team Task Submodule: Team Task Difficulty With rewards The equilibrium formula is: ; The task type coefficients are as follows: Basic Task: 0.5; Advanced Task: 1.0; Challenge Task: 1.5; The reward formula must satisfy the following: ; in, , The adjustment coefficient ( , ); 3. Content quality scoring in the content incentive submodule. The calculation formula is: ; Parameter explanation: The marginal effect diminishes after the word count exceeds 200 words (using a logarithmic function); Image number weight: First Figure 1 0.0, with each subsequent image at 0.5; Keyword matching score: cosine similarity between content keywords and trending topics. When When content is marked as high-quality, an additional 20% points will be awarded; Specific scenarios in the "Points Mall" of this embodiment: Scenario 1, Team Task Incentives: User A (Activity Level 3, Social Influence 1.8) invites friends B (Level 2, Influence 1.2) and C (Level 1, Influence 0.8) to team up and complete the "3-person digital product exchange" task. Basic Rewards Points, task difficulty coefficient 1.0, then: , Points per person; Scenario 2: Content Incentive Mechanism A user published a 250-word review of a digital product. ), received 15 likes and 8 comments, basic reward Points, activity level 3, then: integral, integral.

[0030] The cross-platform points interoperability mechanism in step S7 includes: Establish interface protocols with external platforms to obtain users' points data on those platforms; An exchange rate mapping table is established based on the points type of the external platform and the general points in the points mall. The exchange rate mapping table is dynamically updated based on the user activity and points value of the external platform. After a user submits a redemption request, the system automatically verifies the redemption eligibility and completes the points conversion. The converted general points can be used for all redemption scenarios within the points mall.

[0031] The methods for dynamically adjusting the points acquisition rules and product redemption thresholds in step S8 include: When a user's points exceed a preset threshold, the redemption threshold for high-value goods is increased, while the redemption threshold for low-value goods is decreased. When a user's activity level decreases, increase the point rewards for basic tasks and reduce the point consumption for advanced tasks. We adjust the point weighting and task difficulty coefficient of behaviors in real time based on marketing activities and user feedback.

[0032] The feedback collection module gathers user opinions on task design, points rules, and product redemption, and optimizes the points mall's operation strategy based on these opinions.

[0033] like Figure 2 As shown, this embodiment also provides a user activity enhancement system based on an points mall, including: The data collection module is configured to collect basic behavioral data of users within the points mall; The points calculation module is configured to calculate the user's real-time points value based on the preset mapping relationship between behavior type and points weight, and dynamically adjust the points weight according to the user's activity level. The user profile building module is configured to build user profiles based on users' historical behavior data, including consumption preferences, points usage habits, and activity cycle characteristics. The task generation module is configured to generate a personalized task pool that includes basic tasks, advanced tasks, and social sharing tasks based on user profiles. The task push module is configured to push a list of tasks when the user triggers the conditions for participating in a task, and update the points value according to the task completion status. The social interaction module is configured to set up social interaction scenarios within the points mall, allowing users to earn extra points rewards through social behaviors. The cross-platform interoperability module is configured to establish a cross-platform points interoperability mechanism, allowing users to redeem points from other platforms; The strategy optimization module is configured to dynamically adjust the points rules and operational strategies based on user points, activity levels, and feedback.

[0034] The integral calculation module includes: The weight adjustment submodule is configured to increase the weight of high-frequency behaviors and decrease the weight of low-frequency behaviors when the user's activity level increases; and decrease the weight of high-frequency behaviors and increase the weight of low-frequency behaviors when the user's activity level decreases. The real-time calculation submodule is configured to dynamically update user points based on real-time user behavior data and adjusted point weights.

[0035] The social interaction module includes: The relationship network submodule is configured to establish a user's social relationship network, displaying friends' point rankings, task progress, and redemption records; The team task submodule is configured to design team tasks, where users need to team up with friends to complete tasks and earn bonus points. The content incentive submodule is configured to set up a topic discussion area where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a threshold, a points doubling reward is triggered.

[0036] The cross-platform interoperability module includes: The interface protocol submodule is configured to establish an interface protocol with an external platform to obtain the user's points data on the external platform; The exchange rate mapping submodule is configured to dynamically update the exchange rate mapping table based on user activity and points value on external platforms. The redemption processing submodule is configured to verify the user's redemption eligibility and complete the points conversion. The converted general points can be used for all redemption scenarios in the points mall.

[0037] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for improving user activity based on an points mall, characterized in that, The method includes the following steps: Step S1: Collect basic behavioral data of users in the points mall, including: login frequency, product browsing history, points acquisition and consumption history; Step S2: Calculate the user's real-time points value according to the preset mapping relationship between behavior type and points weight, wherein the points weight is dynamically adjusted according to the user's activity level; Step S3: Construct a user profile based on the user's historical behavior data. The user profile includes: consumption preferences, points usage habits, and activity cycle characteristics. Step S4: Generate a personalized task pool based on the user profile in step S3. The personalized task pool includes: basic tasks, advanced tasks, and social fission tasks. Step S5: When the user triggers the task participation conditions, push the task list from the personalized task pool in step S4 to the user, and update the points value in real time according to the task completion status. Step S6: Set up social interaction scenarios in the points mall, where users can earn extra points by inviting friends, forming teams to complete tasks, or participating in topic discussions; Step S7: Establish a cross-platform points exchange mechanism, allowing users to exchange points from other platforms for universal points in the points mall at a preset exchange rate; Step S8: Dynamically adjust the points acquisition rules and product redemption thresholds based on user points and activity level.

2. The method for improving user activity based on an points mall according to claim 1, characterized in that, In step S2, the dynamic adjustment of the integral weights includes: When a user's activity level increases, the weight of points for high-frequency behaviors is increased, while the weight of points for low-frequency behaviors is decreased. When a user's activity level decreases, the weight of high-frequency behaviors in the score is reduced, while the weight of low-frequency behaviors in the score is increased.

3. The method for improving user activity based on an points mall according to claim 1, characterized in that, In step S4, the generation of the personalized task pool includes: The basic tasks are low-difficulty tasks, including daily login and product reviews, which will earn a fixed number of points upon completion. Advanced tasks are medium to high difficulty tasks, including: cumulative spending and consecutive check-ins. Upon completion, you can get tiered point rewards. Social referral tasks are socially oriented tasks, which include: inviting friends to register and forming teams to take on challenges. Upon completion, users can earn dynamic points rewards, which are linked to the activity level of the invited users.

4. The method for improving user activity based on an points mall according to claim 1, characterized in that, In step S6, the social interaction scenario includes: Establish a social network for users, allowing them to view their friends' points rankings, task completion progress, and redemption records; Design team tasks where users need to team up with at least one friend to complete the task. Upon completion, all team members will receive bonus points. A dedicated discussion area is set up where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a certain threshold, a points-doubling reward is triggered.

5. The method for improving user activity based on an points mall according to claim 1, characterized in that, In step S7, the cross-platform points interoperability mechanism includes: Establish interface protocols with external platforms to obtain users' points data on those platforms; An exchange rate mapping table is established based on the points type of the external platform and the general points in the points mall. The exchange rate mapping table is dynamically updated based on the user activity and points value of the external platform. After a user submits a redemption request, the system automatically verifies the redemption eligibility and completes the points conversion. The converted general points can be used for all redemption scenarios within the points mall.

6. The method for improving user activity based on an points mall according to claim 1, characterized in that, In step S8, the dynamic adjustment of the points acquisition rules and the product redemption threshold includes: When a user's points exceed a preset threshold, the redemption threshold for high-value goods is increased, while the redemption threshold for low-value goods is decreased. When a user's activity level decreases, increase the point rewards for basic tasks and reduce the point consumption for advanced tasks. We adjust the point weighting and task difficulty coefficient of behaviors in real time based on marketing activities and user feedback.

7. A system for implementing the user activity enhancement method based on an points mall as described in any one of claims 1-6, characterized in that, The system includes: The data collection module is configured to collect basic behavioral data of users within the points mall; The points calculation module is configured to calculate the user's real-time points value based on the preset mapping relationship between behavior type and points weight, and dynamically adjust the points weight according to the user's activity level. The user profile building module is configured to build user profiles based on users' historical behavior data, including consumption preferences, points usage habits, and activity cycle characteristics. The task generation module is configured to generate a personalized task pool that includes basic tasks, advanced tasks, and social sharing tasks based on user profiles. The task push module is configured to push a list of tasks when the user triggers the conditions for participating in a task, and update the points value according to the task completion status. The social interaction module is configured to set up social interaction scenarios within the points mall, allowing users to earn extra points rewards through social behaviors. The cross-platform interoperability module is configured to establish a cross-platform points interoperability mechanism, allowing users to redeem points from other platforms; The strategy optimization module is configured to dynamically adjust the points rules and operational strategies based on user points, activity levels, and feedback.

8. A user activity enhancement system based on an points mall according to claim 7, characterized in that, The integral calculation module includes: The weight adjustment submodule is configured to increase the weight of high-frequency behaviors and decrease the weight of low-frequency behaviors when the user's activity level increases; and decrease the weight of high-frequency behaviors and increase the weight of low-frequency behaviors when the user's activity level decreases. The real-time calculation submodule is configured to dynamically update user points based on real-time user behavior data and adjusted point weights.

9. A user activity enhancement system based on an points mall according to claim 7, characterized in that, The social interaction module includes: The relationship network submodule is configured to establish a user's social relationship network, displaying friends' point rankings, task progress, and redemption records; The team task submodule is configured to design team tasks, where users need to team up with friends to complete tasks and earn bonus points. The content incentive submodule is configured to set up a topic discussion area where users can earn content contribution points by posting valid content. When the number of likes and comments reaches a threshold, a points doubling reward is triggered.

10. A user activity enhancement system based on an points mall according to claim 7, characterized in that, The cross-platform interoperability module includes: The interface protocol submodule is configured to establish an interface protocol with an external platform to obtain the user's points data on the external platform; The exchange rate mapping submodule is configured to dynamically update the exchange rate mapping table based on user activity and points value on external platforms. The redemption processing submodule is configured to verify the user's redemption eligibility and complete the points conversion. The converted general points can be used for all redemption scenarios in the points mall.

Images