Method, device, equipment and storage medium for improving user retention in a community

Abstract

The present invention provides a method, device, equipment and storage medium for improving user retention in a community, by acquiring user data in a target community, calling a K-means clustering algorithm to process the user data, and generating a clustering result, wherein the user data includes user behavior data and user feature data, then recommending a second user to a first user in the target community according to the clustering result, calling a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on the similarity of the user portrait of the first user, the user portrait of the second user and the task feature; then, acquiring feedback data of the task, processing the feedback data through an LSTM model to analyze the user's behavior trend and update the user feature, and dynamically adjusting the weight of matching the task with the user to form a closed-loop regulation. It improves the retention of users in the community by dynamically adjusting the user portrait and its associated tasks.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a method, device, equipment and storage medium for improving user retention in a community. Background Art

[0002] With the rapid development of social platforms and online services, user retention has become a key indicator of platform success. Improving user activity and retention is crucial to the market competitiveness of the platform. However, the existing user matching and task reward mechanisms are often lacking in specificity and cannot fully meet the increasingly diverse and personalized needs of users.

[0003] User matching in existing technologies is mostly based on a single dimension, which is unable to effectively tap into users' deep-seated interests and behavior patterns, resulting in insufficient interactivity between users and difficulty in stimulating users' enthusiasm for long-term participation in the community.

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

[0005] The present invention discloses a method, device, equipment and storage medium for improving user retention in a community, aiming to improve user retention in the community by dynamically adjusting user portraits and their associated tasks.

[0006] The first embodiment of the present invention provides a method for improving user retention in a community, comprising:

[0007] Acquire user data in the target community, call the K-means clustering algorithm to process the user data, and generate a clustering result, wherein the user data includes user behavior data and user feature data;

[0008] recommending a second user to a first user in the target community according to the clustering result, and calling a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature;

[0009] The feedback data of the task is obtained, and the feedback data is processed through the LSTM model to analyze the user's behavior trend and update the user characteristics, and the weight of matching the task with the user is dynamically adjusted to form a closed-loop regulation.

[0010] Preferably, the step of obtaining user data in the target community, calling a K-means clustering algorithm to process the user data, and generating a clustering result is as follows:

[0011] The user data is processed by the BERT model to generate a user feature vector, and the user feature vector is operated by the K-means clustering algorithm to divide the users into different groups. For each user, the distance between the user and the cluster center is calculated according to the following expression;

[0012]

[0013] is the user’s feature vector, The K-means clustering algorithm is configured to assign the user with the smallest distance to the corresponding cluster center. After all users are assigned to the corresponding cluster center, each cluster center is updated to the mean of the samples to which it belongs. The expression is:

[0014] ;

[0015] in, is the set of all data points of the jth cluster.

[0016] Preferably, the recommending the second user to the first user in the target community according to the clustering result is specifically:

[0017] The cosine similarity is used to measure the similarity of user features within the same clustering result, and the second user who meets the conditions is recommended to the first user.

[0018] Preferably, the feedback data of the task is obtained, and the feedback data is processed by an LSTM model to analyze the user's behavior trend and update the user characteristics:

[0019] Continuously obtain user feedback data, capture the time-varying characteristics of user preferences through the LSTM model, and update user features through a loss function containing regularization. The expression of the loss function containing regularization is:

[0020]

[0021] in, For users The overall rating of For users The actual rating of is the regularization parameter, For user collection, is the square sum of the user portrait label weight vector, is the sum of the squares of the task system weight vector, is the sum of squares of user chat weight vectors, is the square sum of the user post weight vector.

[0022] Preferably, the similarity expression between the user and the task is:

[0023]

[0024] in, The degree of fit between the user and the task, is the user’s feature vector, is the feature vector of the task, is the weight vector of user features, is the weight vector of task features.

[0025] Preferably, the types of tasks include: social interaction tasks, content creation tasks, learning tasks, game tasks, transaction tasks, recommendation and sharing tasks, and feedback tasks.

[0026] Preferably, it also includes:

[0027] Obtain data of tasks completed by users, calculate quartiles of the data, and calculate IQR and outlier range through the quartiles;

[0028] The task strategy and reward are adjusted based on the IQR and outlier range.

[0029] A second embodiment of the present invention provides a device for improving user retention in a community, comprising:

[0030] A clustering unit, used to obtain user data in a target community, call a K-means clustering algorithm to process the user data, and generate a clustering result, wherein the user data includes user behavior data and user feature data;

[0031] a task assignment unit, configured to recommend a second user to a first user in the target community according to the clustering result, and to call a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature;

[0032] The dynamic adjustment unit is used to obtain feedback data of the task, process the feedback data through the LSTM model to analyze the user's behavior trend and update the user's characteristics, and dynamically adjust the weight of matching the task with the user to form a closed-loop regulation.

[0033] A third embodiment of the present invention provides a device for improving user retention in a community, including a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a method for improving user retention in a community as described in any one of the above items.

[0034] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a method for improving user retention in a community as described in any one of the above items.

[0035] Based on the method, device, equipment and storage medium for improving user retention in a community provided by the present invention, user data in a target community is obtained, a K-means clustering algorithm is called to process the user data, and a clustering result is generated, wherein the user data includes user behavior data and user feature data, then a second user is recommended to a first user in the target community according to the clustering result, and a Gale-Shapley matching algorithm is called to provide a task to the first user and the second user, wherein the task is generated based on the similarity of the user portrait of the first user, the user portrait of the second user and the task feature; then, feedback data of the task is obtained, the feedback data is processed by an LSTM model to analyze the user's behavior trend and update the user feature, and the weight of matching the task with the user is dynamically adjusted to form a closed-loop regulation. It improves the retention of users in the community by dynamically adjusting the user portrait and its associated tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of a method for improving user retention in a community provided by the first embodiment of the present invention;

[0037] Figure 2 It is a module diagram of a device for improving user retention in a community provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0040] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0042] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0044] The "first\second" mentioned in the embodiments is only to distinguish similar objects, and does not represent a specific order for the objects. It is understandable that the "first\second" can be interchanged with the specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0045] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0046] The present invention discloses a method, device, equipment and storage medium for improving user retention in a community, aiming to improve user retention in the community by dynamically adjusting user portraits and their associated tasks.

[0047] See also Figure 1 The first embodiment of the present invention provides a method for improving user retention in a community, which can be performed by a device for improving user retention in a community (hereinafter referred to as a retention device), and in particular, is performed by one or more processors in the retention device to implement at least the following steps:

[0048] S101, obtaining user data in a target community, calling a K-means clustering algorithm to process the user data, and generating a clustering result, wherein the user data includes user behavior data and user feature data;

[0049] In this embodiment, the storage device may be a server, a desktop computer, a laptop computer or other terminal with data processing capabilities. The storage device may be installed with a corresponding operating system and application software, and the functions required by this embodiment are realized through the combination of the operating system and the application software.

[0050] Specifically, in this embodiment, a user data set can be formed by comprehensively collecting the user's behavior (such as posting, liking, commenting, etc.) and characteristics (such as age, gender, geographic location, etc.) in the community. Then, the user data can be processed by natural language through the BERT model to convert the user's text data into a high-dimensional feature vector. The high-dimensional feature vector can fully reflect the user's interests, preferences and behavior patterns.

[0051] After generating user feature vectors, the system uses the K-means clustering algorithm to operate on these vectors. It can first randomly select k cluster centers and calculate the distance between each user feature vector and each cluster center using the following expression:

[0052]

[0053] is the user’s feature vector, The K-means clustering algorithm is configured to assign the user with the smallest distance to the corresponding cluster center to form a preliminary user grouping. After all users are assigned to the corresponding cluster center, the cluster center is updated by calculating the mean of the user feature vector within each cluster, and its expression is:

[0054] ;

[0055] in, is the set of all data points of the jth cluster

[0056] S102, recommending a second user to a first user in the target community according to the clustering result, and calling a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature;

[0057] In this embodiment, the retention device can perform a detailed feature comparison based on the user profile of the first user and the user profile of the second user. These user profiles contain information such as user behavior data, interest preferences, and social attributes to ensure the accuracy of the recommendation. In order to measure the similarity of user features in the same clustering result, cosine similarity can be used as the calculation basis. Specifically, the calculation formula of cosine similarity is:

[0058]

[0059] in, and Represent the feature vectors of the first user and the second user respectively. By calculating the cosine similarity, the retention device can effectively identify users with high feature similarity and recommend them to the first user. When the similarity reaches a certain threshold, the qualified second user will be recommended to the first user. Ensure that the recommended users have high interaction potential, thereby enhancing the connection and interaction between users. Based on this, the retention device will provide tasks for the first user and the second user. Of course, it can also provide common tasks for the first user and the second user so that the first user and the second user can restrain each other.

[0060] During the task generation process, the retention device can be dynamically adjusted according to the feature similarity and task features of the first user and the second user, so that the recommended tasks can improve the participation of the first user and the second user. Tasks may include but are not limited to: social interaction tasks, content creation tasks, learning tasks, game tasks, transaction tasks, recommendation and sharing tasks, and feedback tasks; then, by implementing the Gale-Shapley matching algorithm, the system can achieve efficient user recommendation and task allocation based on the clustering results, promote interaction between users, and improve the activity of the community and user retention rate.

[0061] S103, obtaining feedback data of the task, processing the feedback data through the LSTM model to analyze the user's behavior trend and update the user's characteristics, and dynamically adjusting the weight of matching the task with the user to form a closed-loop regulation.

[0062] In this embodiment, the retention device can obtain feedback data from users after completing the task. These feedback data are the basis for the user's interaction with the task. The feedback data may include task completion status (such as completion rate and completion time), user satisfaction, task interaction status, user behavior changes, and reward feedback. By analyzing the feedback data, the user's behavior trends and preference changes can be understood, which are used to update subsequent task recommendations and user features. The retention device can use an LSTM (Long Short-Term Memory Network) model to process these feedback data. It can effectively capture long-term dependencies in time series data and analyze user behavior trends.

[0063] Input this data into the LSTM model, and the model will update the user's hidden state To reflect the user's current behavior patterns and preferences. The state update formula of the LSTM model is:

[0064]

[0065] in, is the current feedback data, is the hidden state of the previous time step. By continuously processing user feedback, the LSTM model can dynamically capture changes in user preferences;

[0066] After processing the feedback data, the system will update the user features through a loss function that includes regularization. The expression of this loss function is:

[0067]

[0068] in, For users The overall rating of For users The actual rating of is the regularization parameter, For user collection, is the square sum of the user portrait label weight vector, is the sum of the squares of the task system weight vector, is the sum of squares of user chat weight vectors, The sum of the squares of the user's post weight vector. By adding regularization terms, it is ensured that the model does not give excessive weights to certain features simply because they appear by chance, preventing overfitting when updating user features and maintaining the generalization ability of the model.

[0069] In order to improve the accuracy of the recommendation, the retention device will also be dynamically adjusted based on the similarity between the user and the task. The similarity between the user and the task is expressed as:

[0070]

[0071] in, The degree of fit between the user and the task, is the user’s feature vector, is the feature vector of the task, is the weight vector of user features, is the weight vector of task features.

[0072] By calculating the similarity, the retention device can update the weight of matching tasks with users in real time to ensure the personalization and relevance of recommended tasks. Ultimately, the dynamic adjustment process forms a closed-loop adjustment mechanism, which enables user characteristics and task recommendations to be continuously optimized based on real-time user feedback. Through an effective feedback loop, the system not only improves the matching degree of tasks, but also enhances the user's sense of participation, thereby achieving an increase in user retention rate.

[0073] In this embodiment, the following may also be included:

[0074] Obtain data of tasks completed by users, calculate quartiles of the data, and calculate IQR and outlier range through the quartiles;

[0075] The task strategy and reward are adjusted based on the IQR and outlier range.

[0076] It should be noted that the retention device will perform statistical analysis on the data collected from users completing tasks to identify potential outliers. Specifically, the retention device will sort the data and calculate the quartiles of the data to determine the first quartile Q1 and the third quartile Q3. By calculating these quartiles, the retention device can determine the distribution of the data and further calculate the interquartile range (IQR); where IQR=Q3-Q1;

[0077] Furthermore, data points that are outside the upper and lower limits are detected in the task completion data and marked as abnormal. These abnormal values ​​are excluded from the analysis to avoid affecting the overall task difficulty or reward distribution. If the completion time or completion rate of certain tasks frequently shows abnormal values, the difficulty of the task can be reduced. If the task completion shows extremely low values ​​(the abnormal values ​​are concentrated in the lower limit), the reward for the task can be increased to increase user participation.

[0078] In this embodiment, the system can also use a machine learning model to learn the changing trend of data distribution based on the data after excluding outliers, and dynamically adjust task recommendations and difficulty.

[0079] See also Figure 2 The second embodiment of the present invention provides a device for improving user retention in a community, including:

[0080] The clustering unit 201 is used to obtain user data in the target community, call the K-means clustering algorithm to process the user data, and generate a clustering result, wherein the user data includes user behavior data and user feature data;

[0081] A task assignment unit 202 is configured to recommend a second user to a first user in the target community according to the clustering result, and to call a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature;

[0082] The dynamic adjustment unit 203 is used to obtain feedback data of the task, process the feedback data through the LSTM model to analyze the user's behavior trend and update the user characteristics, and dynamically adjust the weight of matching the task with the user to form a closed-loop regulation.

[0083] A third embodiment of the present invention provides a device for improving user retention in a community, including a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a method for improving user retention in a community as described in any one of the above items.

[0084] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a method for improving user retention in a community as described in any one of the above items.

[0085] Based on the method, device, equipment and storage medium for improving user retention in a community provided by the present invention, user data in a target community is obtained, a K-means clustering algorithm is called to process the user data, and a clustering result is generated, wherein the user data includes user behavior data and user feature data, then a second user is recommended to a first user in the target community according to the clustering result, and a Gale-Shapley matching algorithm is called to provide a task to the first user and the second user, wherein the task is generated based on the similarity of the user portrait of the first user, the user portrait of the second user and the task feature; then, feedback data of the task is obtained, the feedback data is processed by an LSTM model to analyze the user's behavior trend and update the user feature, and the weight of matching the task with the user is dynamically adjusted to form a closed-loop regulation. It improves the retention of users in the community by dynamically adjusting the user portrait and its associated tasks.

[0086] Exemplarily, the computer program described in the third and fourth embodiments of the present invention may be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the device for implementing a method for improving user retention in the community. For example, the device described in the second embodiment of the present invention.

[0087] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the method for improving user retention in the community, and uses various interfaces and lines to connect the various parts of the method for improving user retention in the community.

[0088] The memory can be used to store the computer program and / or module, and the processor can realize various functions of a method for improving user retention in the community by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0089] Wherein, if the implemented module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0090] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0091] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for improving user retention in a community, characterized in that: include: Acquire user data in the target community, call the K-means clustering algorithm to process the user data, and generate a clustering result, wherein the user data includes user behavior data and user feature data; recommending a second user to a first user in the target community according to the clustering result, and calling a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature; The feedback data of the task is obtained, and the feedback data is processed through the LSTM model to analyze the user's behavior trend and update the user characteristics, and the weight of matching the task with the user is dynamically adjusted to form a closed-loop regulation.

2. A method for improving user retention in a community according to claim 1, characterized in that: The step of obtaining user data in the target community, calling the K-means clustering algorithm to process the user data, and generating a clustering result is as follows: The user data is processed by the BERT model to generate a user feature vector, and the user feature vector is operated by the K-means clustering algorithm to divide the users into different groups. For each user, the distance between the user and the cluster center is calculated according to the following expression; is the user’s feature vector, The K-means clustering algorithm is configured to assign the user with the smallest distance to the corresponding cluster center. After all users are assigned to the corresponding cluster center, each cluster center is updated to the mean of the samples to which it belongs. The expression is: ； in, is the set of all data points of the jth cluster.

3. A method for improving user retention in a community according to claim 1, characterized in that: The recommending the second user to the first user in the target community according to the clustering result is specifically: The cosine similarity is used to measure the similarity of user features within the same clustering result, and the second user who meets the conditions is recommended to the first user.

4. A method for improving user retention in a community according to claim 1, characterized in that: The feedback data of the task is obtained, and the feedback data is processed by the LSTM model to analyze the user's behavior trend and update the user characteristics: Continuously obtain user feedback data, capture the time-varying characteristics of user preferences through the LSTM model, and update user features through a loss function containing regularization. The expression of the loss function containing regularization is: in, For users The overall rating of For users The actual rating of is the regularization parameter, For user collection, is the square sum of the user portrait label weight vector, is the sum of the squares of the task system weight vector, is the sum of squares of user chat weight vectors, is the square sum of the user post weight vector.

5. A method for improving user retention in a community according to claim 1, characterized in that: The similarity expression between users and tasks is: in, The degree of fit between the user and the task, is the user’s feature vector, is the feature vector of the task, is the weight vector of user features, is the weight vector of task features.

6. A method for improving user retention in a community according to claim 1, characterized in that: The types of tasks include: social interaction tasks, content creation tasks, learning tasks, game tasks, transaction tasks, recommendation and sharing tasks, and feedback tasks.

7. A method for improving user retention in a community according to claim 1, characterized in that: Also includes: Obtain data of tasks completed by users, calculate quartiles of the data, and calculate IQR and outlier range through the quartiles; The task strategy and reward are adjusted based on the IQR and outlier range.

8. A device for improving user retention in a community, characterized in that: include: A clustering unit, used to obtain user data in a target community, call a K-means clustering algorithm to process the user data, and generate a clustering result, wherein the user data includes user behavior data and user feature data; a task assignment unit, configured to recommend a second user to a first user in the target community according to the clustering result, and to call a Gale-Shapley matching algorithm to provide a task to the first user and the second user, wherein the task is generated based on a similarity between a user profile of the first user, a user profile of the second user, and a task feature; The dynamic adjustment unit is used to obtain feedback data of the task, process the feedback data through the LSTM model to analyze the user's behavior trend and update the user's characteristics, and dynamically adjust the weight of matching the task with the user to form a closed-loop regulation.

9. A device for improving user retention in a community, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a method for improving user retention in a community as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a method for improving user retention in a community as described in any one of claims 1 to 7.

Images