User identification processing method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to a user identification processing method and device, electronic equipment and storage medium. The method comprises: obtaining personal attribute information corresponding to a user identification; the personal attribute information comprises a corresponding task sequence, an interaction state of each task in the task sequence and user information, the task sequence comprises at least one task, and the interaction state is an interaction state of a resource in the process of performing each task; inputting the personal attribute information into a user type identification model to identify the user type, and obtaining a user type corresponding to the user identification; and when the user type is consistent with a preset type, starting a preset protection strategy for the user identification. According to the present disclosure, it can be judged whether the user is of a preset type that needs protection, and the preset protection strategy is started for the user that needs to be started, the protection strategy is started for the user that needs protection, the protection strategy is started without difference, the system resources are saved, the purpose of improving user experience and retaining new users is achieved.

Description

Technical Field

[0001] This disclosure relates to the field of Internet technology, and in particular to a user identification processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of internet technology and people's diversified demands for cultural life and leisure activities, the development and application of various shopping, short video, and game applications have experienced unprecedented growth. When developing an application product, it's necessary to consider how to attract and retain new users, turning novice users into core users and improving user retention rates. Therefore, in developing online virtual game scenarios, a traditional method to improve user retention is to indiscriminately enable protection policies for new users, allowing them to better participate in interactions.

[0003] However, traditional methods for improving user retention cannot be flexibly adjusted for different users, resulting in a waste of system resources. Summary of the Invention

[0004] This disclosure provides a user identification processing method, apparatus, electronic device, and storage medium to at least solve the problem in related technologies that cannot flexibly adjust for different users. The technical solution of this disclosure is as follows:

[0005] According to a first aspect of the present disclosure, a user identifier processing method is provided, including:

[0006] Obtain personal attribute information corresponding to the user identifier; the personal attribute information includes the corresponding task sequence, the interaction status of each task in the task sequence, and user information, wherein the task sequence includes at least one task, and the interaction status is the interaction status of resources during the performance of each task;

[0007] The personal attribute information is input into the user type recognition model to identify the user type and obtain the user type corresponding to the user identifier; the user type recognition model is trained based on the historical personal attribute information of the sample users.

[0008] When the user type matches the preset type, a preset protection strategy is activated for the user identifier; wherein, the preset type is a user type whose proficiency in completing the task is less than a first preset threshold, and the proficiency represents the user's level of proficiency in completing the task.

[0009] In one exemplary embodiment, the preset protection strategy includes: a protection strategy for allocating preset resources to users corresponding to the preset type during the performance of a task.

[0010] In one exemplary embodiment, obtaining the personal attribute information corresponding to the user identifier includes:

[0011] Detect the number of tasks in the task sequence;

[0012] When the number of tasks is less than the second preset threshold, the personal attribute information corresponding to the user identifier is obtained.

[0013] In one exemplary embodiment, the method for obtaining the user type identification model includes:

[0014] Obtain the historical personal attribute information corresponding to the sample users;

[0015] Based on the historical personal attribute information, determine the user type corresponding to the user identifier;

[0016] Using the historical personal attribute information as input and the user type as supervision information, a preset initial recognition model is trained to obtain the user type recognition model.

[0017] In an exemplary embodiment, determining the user type corresponding to the user identifier based on the historical personal attribute information includes:

[0018] After the completion of at least one task, the task is terminated, and the user type corresponding to the user identifier is determined as the user type that needs to be protected; wherein the number of the at least one task is less than a third preset threshold.

[0019] In one exemplary embodiment, the user information in the historical personal attribute information includes the login status corresponding to the user identifier;

[0020] The step of determining the user type corresponding to the user identifier based on the historical personal attribute information includes:

[0021] Within a preset time period, the login status corresponding to the user identifier is detected, and the login count corresponding to the user identifier is obtained;

[0022] If the number of logins corresponding to the user identifier is less than the fourth preset threshold within the preset time period, then the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0023] In one exemplary embodiment, the interaction state in the historical personal attribute information includes the number of interactions during the process of performing each of the tasks;

[0024] The step of determining the user type corresponding to the user identifier based on the historical personal attribute information includes:

[0025] Detect the number of interactions during the process of performing each of the tasks described;

[0026] If the number of interactions during each of the tasks is less than a fifth preset threshold, then the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0027] According to a second aspect of the present disclosure, a user identifier processing apparatus is provided, comprising:

[0028] A personal attribute information acquisition unit is configured to acquire personal attribute information corresponding to a user identifier; the personal attribute information includes a corresponding task sequence, the interaction state of each task in the task sequence, and user information, wherein the task sequence includes at least one task, and the interaction state is the interaction state of resources during the performance of each task;

[0029] The user type determination unit is configured to input the personal attribute information into the user type recognition model to perform user type recognition and obtain the user type corresponding to the user identifier; the user type recognition model is trained based on the historical personal attribute information of the sample user.

[0030] The user identifier processing unit is configured to execute a preset protection strategy for the user identifier when the user type matches a preset type; wherein the preset type is a user type whose proficiency in completing the task is less than a first preset threshold, and the proficiency characterizes the user's proficiency in completing the task.

[0031] In an exemplary embodiment, the user identification processing device further includes a protection policy storage unit configured to store the preset protection policy, the preset protection policy including: a protection policy for allocating preset resources to users corresponding to the preset type during the performance of a task.

[0032] In one exemplary embodiment, the personal attribute information acquisition unit is further configured to perform:

[0033] Detect the number of tasks in the task sequence;

[0034] When the number of tasks is less than the second preset threshold, the personal attribute information corresponding to the user identifier is obtained.

[0035] In one exemplary embodiment, the user identifier processing apparatus further includes a user type identification model determination unit, configured to perform:

[0036] Obtain the historical personal attribute information corresponding to the sample users;

[0037] Based on the historical personal attribute information, determine the user type corresponding to the user identifier;

[0038] Using the historical personal attribute information as input and the user type as supervision information, a preset initial recognition model is trained to obtain the user type recognition model.

[0039] In one exemplary embodiment, the user type identification model determination unit is further configured to perform:

[0040] After the completion of at least one task, the task is terminated, and the user type corresponding to the user identifier is determined as the user type that needs to be protected; wherein the number of the at least one task is less than a third preset threshold.

[0041] In one exemplary embodiment, the user information in the historical personal attribute information includes the login status corresponding to the user identifier;

[0042] The user type identification model determination unit is also configured to perform:

[0043] Within a preset time period, the login status corresponding to the user identifier is detected, and the login count corresponding to the user identifier is obtained;

[0044] If the number of logins corresponding to the user identifier is less than the fourth preset threshold within the preset time period, then the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0045] In one exemplary embodiment, the interaction state in the historical personal attribute information includes the number of interactions during the process of performing each of the tasks;

[0046] The user type identification model determination unit is also configured to perform:

[0047] Detect the number of interactions during the process of performing each of the tasks described;

[0048] If the number of interactions during each of the tasks is less than a fifth preset threshold, then the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0049] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0050] processor;

[0051] Memory used to store the processor's executable instructions;

[0052] The processor is configured to execute the instructions to implement the user identifier processing method described in any of the embodiments of the first aspect above.

[0053] According to a fourth aspect of the present disclosure, a storage medium is provided that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the user identification processing method described in any of the embodiments of the first aspect.

[0054] According to a fifth aspect of the present disclosure, a computer program product is provided, the program product including a computer program stored in a readable storage medium, wherein at least one processor of a device reads from the readable storage medium and executes the computer program, causing the device to perform the user identification processing method described in any of the embodiments of the first aspect above.

[0055] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0056] The system acquires the personal attribute information corresponding to the user identifier. This personal attribute information includes the corresponding task sequence, the interaction state of each task in the task sequence, and user information. The task sequence includes at least one task, and the interaction state refers to the resource interaction state during each task. The personal attribute information is input into a user type recognition model for user type identification to obtain the user type corresponding to the user identifier. The model then determines whether the user type matches a preset type. If the user type matches the preset type, it is considered that the user type is not proficient in the interaction skills required to complete the above tasks, and a protection policy needs to be activated during task completion. This allows for targeted activation of protection policies for users who require protection, avoiding indiscriminate activation of protection policies, saving system resources, and further improving user experience and retention rates through personalized protection policies.

[0057] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0059] Figure 1 This is an application environment diagram illustrating a user identification processing method according to an exemplary embodiment.

[0060] Figure 2 This is a flowchart illustrating a user identification processing method according to an exemplary embodiment.

[0061] Figure 3 This is a flowchart illustrating one possible implementation of step S100 according to an exemplary embodiment.

[0062] Figure 4 This is a flowchart illustrating a method for obtaining a user type identification model according to an exemplary embodiment.

[0063] Figure 5 This is a flowchart illustrating a user identification processing method according to a specific exemplary embodiment.

[0064] Figure 6 This is a block diagram illustrating a user identification processing apparatus according to an exemplary embodiment.

[0065] Figure 7 This is a block diagram illustrating a device for user identification processing according to an exemplary embodiment. Detailed Implementation

[0066] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0067] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0068] Figure 1 This is an application environment diagram illustrating a user identification processing method according to an exemplary embodiment. The user identification processing method provided in this disclosure can be applied to, for example... Figure 1 In the application environment shown, electronic device 110 interacts with server 120 via a network. Electronic device 110 obtains the user's identifier and corresponding personal attribute information, inputs the personal attribute information into a user type recognition model for user type recognition, obtains the user type corresponding to the user identifier, and determines whether the user type matches a preset type. If the user type matches the preset type, a preset protection policy is activated for that user identifier. Electronic device 110 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. Server 120 can be a standalone server or a server cluster consisting of multiple servers.

[0069] Figure 2 This is a flowchart illustrating a user identification processing method according to an exemplary embodiment, such as... Figure 2 As shown, the user identifier processing method is used for Figure 1 Taking electronic device 110 as an example, the explanation includes the following steps:

[0070] In step S100, personal attribute information corresponding to the user identifier is obtained; the personal attribute information includes the corresponding task sequence, the interaction status of each task in the task sequence, and user information, wherein the task sequence includes at least one task, and the interaction status is the interaction status of resources during the process of performing each task.

[0071] In step S200, personal attribute information is input into the user type recognition model to identify the user type and obtain the user type corresponding to the user identifier; the user type recognition model is trained based on the historical personal attribute information of the sample user.

[0072] In step S300, when the user type matches the preset type, a preset protection strategy is activated for the user identifier; wherein, the preset type is the user type whose proficiency in completing the task is less than a preset threshold, and proficiency represents the user's level of proficiency in completing the task.

[0073] Here, user identifier refers to the identifier used to identify a user, such as user ID or user IP address. Task sequence refers to the sequence of behaviors formed when a user identifier completes one or more tasks. This task sequence includes information such as interaction duration and the number of interaction rounds within a preset duration. For example, when the task corresponds to a game scenario, the interaction duration could be the time and duration the user played the game, and the number of interaction rounds could be the number of game rounds participated in within the preset duration. Interaction status refers to the interaction situation during task completion, which can include the interaction results and resource value changes within the task. For example, interaction status includes wins and losses, and the entry and exit of coins in a game scenario. User information refers to the user's personal information, such as the user's login status when completing a task, their geographical location, age, and followed streamers. Proficiency refers to a quantitative indicator measuring a user's level of skill in completing a task. For example, a value of 1 can be used: proficiency of 1 indicates the user can complete the task proficiently, proficiency of 0.8 indicates the user can complete the task relatively proficiently, proficiency of 0.5 indicates the user cannot complete the task relatively proficiently, and proficiency of 0 indicates the user cannot complete the task proficiently. Preset type refers to the user's attribute type. For example, if a user's proficiency in completing a task is less than a first preset threshold, or if the user is a novice requiring protection policies, then the corresponding protection policy can be activated based on the user type. Optionally, the preset protection policy includes: a protection policy that allocates preset resources to users corresponding to the preset type during a task. Optionally, when the task is a game, the preset resources can be a good game configuration (or a poor game configuration) to allow users to have a different experience in the game.

[0074] Specifically, the system acquires the personal attribute information corresponding to a user identifier and inputs this information into a user type recognition model. The model then identifies the user type corresponding to that identifier. This user type recognition model is trained using historical personal attribute information from a large sample of selected users. Based on the input personal attribute information, the trained model can determine the user type corresponding to the user identifier. After obtaining the user type, the system further determines whether it matches a preset type. If the user type matches the preset type, the user type corresponding to the user identifier is considered a user requiring protection. In this case, a preset protection policy is activated for this user type, enabling targeted activation of protection policies for users requiring protection.

[0075] The aforementioned user identification processing method obtains the personal attribute information corresponding to the user identifier. This personal attribute information includes the corresponding task sequence, the interaction state of each task in the task sequence, and user information. The task sequence includes at least one task, and the interaction state refers to the resource interaction state during each task. The personal attribute information is input into a user type recognition model for user type identification to obtain the user type corresponding to the user identifier. It is then determined whether the user type matches a preset type. If the user type matches the preset type, it is considered that the user type is not proficient in the interaction skills required to complete the above task, and a protection strategy needs to be activated during task completion. This allows for targeted activation of protection strategies for users requiring protection, avoiding indiscriminate activation of protection strategies, saving system resources, and further improving user experience and retention rates through personalized protection strategies.

[0076] Figure 3 This is a flowchart illustrating one possible implementation of step S100 according to an exemplary embodiment, such as... Figure 3 As shown, step S100 specifically includes the following steps:

[0077] In step S110, the number of tasks in the task sequence is detected.

[0078] In step S120, when the number of tasks is less than the second preset threshold, the personal attribute information corresponding to the user identifier is obtained.

[0079] The number of tasks refers to the number of tasks completed in the task sequence. For example, when a task is a game, the number of tasks is the number of matches played in the game. For instance, in the game of Dou Dizhu (a popular Chinese card game), each game played is considered a task. The second preset threshold is a threshold for determining the user type that requires enabling protection policies, based on the actual task. The second preset threshold can be 20, 30, or 40. For example, if the second preset threshold is 20, a newly registered game account user who has played very few games in this game scenario, perhaps only 10 games, is considered a novice who cannot skillfully complete a game, and their user type is a preset type that requires enabling protection policies.

[0080] Specifically, the system detects the number of tasks in a task sequence. If the number of tasks is less than a second preset threshold, it's assumed that the user's proficiency level might be less than a first preset threshold. However, there's also a possibility that the user's task count is less than the second preset threshold, but their proficiency level is not less than the first preset threshold. In this case, it's necessary to further obtain the user's personal attribute information to determine if the user's proficiency level is less than the first preset threshold, requiring a protection strategy. If the number of tasks is not less than the second preset threshold, it's assumed that the user's proficiency level is not less than the first preset threshold, and no protection strategy needs to be activated. Therefore, it's also unnecessary to obtain the user's personal attribute information for user type identification. Thus, only users with fewer than the second preset threshold need further verification, saving system resources.

[0081] In the above exemplary embodiment, the number of tasks in the task sequence is detected. When the number of tasks is less than a second preset threshold, the personal attribute information corresponding to the user identifier is obtained to further verify whether the user's proficiency level is less than a first preset threshold, thus requiring a protection strategy. When the number of tasks is less than the second preset threshold, no further verification is needed, nor is it necessary to obtain the personal attribute information corresponding to the user identifier, thereby saving system operating resources.

[0082] Figure 4 This is a flowchart illustrating a method for obtaining a user type identification model according to an exemplary embodiment, such as... Figure 4 As shown, the specific steps include:

[0083] In step S210, the historical personal attribute information corresponding to the sample user is obtained.

[0084] In step S220, the user type corresponding to the user identifier is determined based on the historical personal attribute information.

[0085] In step S230, the user type identification model is trained using historical personal attribute information as input and user type as supervision information to obtain a user type identification model.

[0086] Specifically, the historical personal attribute information of sample users is obtained. Based on this information, the user type corresponding to the user identifier is determined. User types include preset types and other types. The historical personal attribute information is then used as input to train a preset initial recognition model. The structure and parameters of the initial recognition model are adjusted using the user type as supervision information (or the desired output), ultimately resulting in a user type recognition model.

[0087] Optionally, after at least one task is completed, the task is terminated, and the user type corresponding to the user identifier is determined as the user type that needs to be protected; wherein the number of at least one task is less than a third preset threshold.

[0088] The third preset threshold is a small value, which can be 1, 5, 10, 20, etc. If the number of at least one task is less than the third preset threshold, it is considered that the user cannot master the skills to complete the task and is a preset type of user that needs to be protected.

[0089] Specifically, a user's experience during a task can be assessed based on whether they choose to continue to the next task after completing one or more tasks. This allows for further identification of the user type. If a user chooses to continue, it indicates a positive experience, suggesting they have mastered the necessary skills and are not a pre-defined user type requiring protection. Conversely, if a user chooses to quit, it suggests a potentially negative experience, indicating they haven't mastered the required skills and are a pre-defined user type requiring protection. When the task is a game, specifically within the game scenario, if a user ends their interaction after one round, it suggests they may be dissatisfied with the game experience. This is typically due to repeated losses and resulting frustration. In this case, the user type corresponding to this user identifier is identified as a pre-defined type requiring protection. For example, if a user identifier ends their interaction after the Mth round, it suggests they may be dissatisfied with the game experience, and the user type corresponding to this identifier is identified as a pre-defined type requiring protection after the Mth round. If the user identifier continues to interact after the Mth round of interaction, the user type corresponding to the user identifier will be determined as a non-preset type that does not require enabling the protection policy after the Mth round of interaction. If the user identifier ends the interaction after the M+Nth round of interaction, the user type corresponding to the user identifier will be determined as a preset type that requires enabling the protection policy after the M+Nth round of interaction.

[0090] Optionally, within a preset time period, the login status corresponding to the user identifier is detected to obtain the login count corresponding to the user identifier; if the login count corresponding to the user identifier is less than the fourth preset threshold within the preset time period, the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0091] The user information in the historical personal attribute information includes the login status corresponding to the user identifier. The preset time period is a baseline unit of time, which can be one day, two days, one week, two weeks, or one month. The fourth preset threshold is a small value, which can be 1, 5, 10, or 20. If the number of logins is less than the fourth preset threshold, the user is considered to lack the skills to complete the task and is a preset type of user that requires protection.

[0092] Specifically, the user's experience in the task system is judged based on the number of times the user logs in within a preset time period, further determining the user type. When the number of logins is greater than a fourth preset threshold, it indicates that the user logs in frequently and may have a good experience during the task, suggesting that the user has mastered the skills to complete the task and is not a preset type of user requiring protection. When the number of logins is less than or equal to the fourth preset threshold, it indicates that the user logs in infrequently and may have a poor experience during the task, suggesting that the user has not mastered the skills to complete the task and is a preset type of user requiring protection. When the task is a game, specifically in the game scenario, based on the login status corresponding to the user identifier, the number of times the user is online within a preset time period is detected. Within the preset time period, the relationship between the login count corresponding to the user identifier and the fourth preset threshold is compared. When the login count corresponding to the user identifier is less than the fourth preset threshold, it indicates that the user has interacted with the game less frequently within the preset time period, suggesting that the user may be dissatisfied with the game experience. This situation is generally caused by the user consistently losing in the game, leading to low mood. Therefore, the user type corresponding to the user identifier is determined as a preset type requiring protection policies.

[0093] Optionally, the number of interactions during each task is detected; if the number of interactions during each task is less than a fifth preset threshold, the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0094] The interaction status in the historical personal attribute information includes the number of interactions during each task. The fifth preset threshold is a small value, which can be 1, 5, 10, or 20. If the number of interactions is less than the fifth preset threshold, the user is considered to lack the skills to complete the task and is a preset type of user requiring protection. The fifth preset threshold is based on the average number of interactions for each user determined from the sample users. This average number of interactions changes continuously based on the task's release time and user usage, and can be updated every week, month, or six months.

[0095] Specifically, the user's experience within a task is assessed based on the number of interactions performed, further determining the user type. If the number of interactions exceeds a fifth preset threshold, it indicates the user was fully engaged in the task, likely had a positive experience, and is considered to have mastered the necessary skills; this user is not a preset type requiring protection. Conversely, if the number of interactions is less than or equal to the fifth preset threshold, it indicates the user was not fully engaged in the task, likely had a poor experience, and is considered to have not mastered the necessary skills; this user is a preset type requiring protection. When the task is a game, specifically within the game scenario, the number of interactions corresponding to a user identifier is detected. If the number of interactions is less than the fifth preset threshold, it is assumed the user may be dissatisfied with their game experience, typically due to repeated losses and resulting frustration. In this case, the user type corresponding to that identifier is identified as a preset type requiring protection policies.

[0096] In the above exemplary embodiment, by obtaining the historical personal attribute information corresponding to the sample user, and determining the user type corresponding to the user identifier based on the historical personal attribute information, the user type identification model is trained using the historical personal attribute information as input and the user type as supervision information. This provides a basis for determining the user type based on personal attribute information and enables the activation of a preset protection strategy for users of the preset type, thereby enabling targeted protection strategies for users who need protection.

[0097] Figure 5 This is a flowchart illustrating a user identification processing method according to a specific exemplary embodiment, such as... Figure 5 As shown, the user identifier processing method is used for Figure 1 Taking electronic device 110 as an example, in a specific scenario, a task is a game, and the interaction in the task is the interaction in the game, which specifically includes the following steps:

[0098] In step S501, log in to the game; when a new user registers and enters the product, the user will be marked as a "newbie" (a user of the default type) and enter the "newbie protection period".

[0099] In step S502, the game is played; new users play the game during the protection period, and after each game, the system will make a model request for the user type recognition model.

[0100] In step S503, the model requests that the system input the new user's personal attribute information (user information, past behavior sequences or task sequences, including the user's behavior on other platforms, previous game results on this platform, etc.) into the user type recognition model. The user type recognition model will output 1 (preset type) or 0 (non-preset type).

[0101] In step S504, the system determines whether to use a strategy. If the user type recognition model outputs 0, the user continues to participate in the system's matching process normally. If the user type recognition model outputs 1, the system will trigger a novice protection strategy, providing novice players with a low-difficulty game. For example, in a Dou Dizhu (a popular Chinese card game) scenario, the system matches the novice player with an AI robot based on simple rules and deals them a "good hand," such as a large number of high-ranking cards or bombs.

[0102] Optionally, once a new user's total number of game rounds reaches a certain threshold, the user's "new user" label will be removed and the "new user protection period" will end.

[0103] Optionally, when applying the user type identification model, to obtain accurate model output that guides the triggering of the novice protection strategy, various "Proxy Labels" are designed for the sample data to approximate whether the model needs to trigger. A sample is defined as the period from the end of each game for a novice user to the start of the next game, based on their historical personal attribute information. The sample's features include the user's behavioral sequence and statistical characteristics before this point in time (interaction status in the virtual scenario, such as recent wins and losses, coin inflows and outflows, etc.) and the user's personal information (such as geographical location, age, and which streamers they have followed on the main site). After determining the historical personal attribute information for the sample users, various methods are used to define labels so that the model can correctly trigger the protection strategy. For example, a label of 1 indicates the user immediately logs off after the current game ends, otherwise 0; a label of 1 indicates the user immediately logs off after losing another game after the current game ends, otherwise 0; a label of 1 indicates whether the user's retention rate is significantly lower than the average after the current game ends; and a label of 1 indicates whether the average number of games played by the user is significantly lower than the average after the current game ends.

[0104] After obtaining samples, features, and proxy labels from historical data, a training set for a classification model can be constructed. This training set will then be used to train a GBDT classification model. Due to the method of constructing the training set, the model's input can be abstracted as "the objective state of a player after finishing a game," and the output can be abstracted as "the risk of the player experiencing low mood." When used online, a protection strategy is triggered when the risk value is high enough (model output 1).

[0105] In the above exemplary embodiment, a model that can trigger protection policies can be trained using historical data through the design of Proxy Label. Based on historical behavior, it can analyze whether different users are at risk of churn in different scenarios, thereby providing intelligent and personalized protection policies and improving user retention.

[0106] It should be understood that, although Figure 2-5 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-5 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0107] Figure 6 This is a block diagram illustrating a user identification processing apparatus according to an exemplary embodiment. (Refer to...) Figure 6 The device includes a personal attribute information acquisition unit 601, a user type determination unit 602, and a user identifier processing unit 603.

[0108] The personal attribute information acquisition unit 601 is configured to acquire personal attribute information corresponding to the user identifier; the personal attribute information includes the corresponding task sequence, the interaction state of each task in the task sequence, and user information, wherein the task sequence includes at least one task, and the interaction state is the interaction state of resources during the performance of each task.

[0109] User type determination unit 602 is configured to input personal attribute information into user type recognition model to perform user type recognition and obtain the user type corresponding to the user identifier; the user type recognition model is trained based on the historical personal attribute information of the sample user.

[0110] User identification processing unit 603 is configured to execute a preset protection strategy for user identification when the user type matches the preset type; wherein the preset type is a user type whose proficiency in completing the task is less than a first preset threshold, and proficiency represents the user's proficiency in completing the task.

[0111] In one exemplary embodiment, the user identification processing apparatus further includes a protection policy storage unit configured to store a preset protection policy, the preset protection policy including: a protection policy for allocating preset resources to users corresponding to a preset type during the performance of a task.

[0112] In an exemplary embodiment, the personal attribute information acquisition unit 601 is further configured to perform: detecting the number of tasks in the task sequence; and when the number of tasks is less than a second preset threshold, acquiring personal attribute information corresponding to the user identifier.

[0113] In an exemplary embodiment, the user identifier processing apparatus further includes a user type recognition model determination unit, configured to perform: acquiring historical personal attribute information corresponding to the sample user; determining the user type corresponding to the user identifier based on the historical personal attribute information; and training a preset initial recognition model using the historical personal attribute information as input and the user type as supervision information to obtain a user type recognition model.

[0114] In an exemplary embodiment, the user type identification model determination unit is further configured to: after at least one task is completed, terminate the task, and determine the user type corresponding to the user identifier as the user type that needs to be protected; wherein the number of at least one task is less than a third preset threshold.

[0115] In an exemplary embodiment, the user information in the historical personal attribute information includes the login status corresponding to the user identifier; the user type identification model determination unit is further configured to perform: within a preset time period, detect the login status corresponding to the user identifier and obtain the login count corresponding to the user identifier; if within the preset time period, the login count corresponding to the user identifier is less than a fourth preset threshold, then the user type corresponding to the user identifier is determined as the user type that needs to be protected.

[0116] In an exemplary embodiment, the interaction state in the historical personal attribute information includes the number of interactions during each task; the user type identification model determination unit is further configured to perform: detecting the number of interactions during each task; if the number of interactions during each task is less than a fifth preset threshold, then determining the user type corresponding to the user identifier as the user type that needs to be protected.

[0117] Regarding the apparatus in the above embodiments, the specific manner in which each unit performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here. Figure 7 This is a block diagram illustrating a device 700 for user identification processing according to an exemplary embodiment. For example, device 700 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0118] Reference Figure 7The device 700 may include one or more of the following components: processing component 702, memory 704, power component 706, multimedia component 708, audio component 710, input / output (I / O) interface 712, sensor component 714, and communication component 716.

[0119] Processing component 702 typically controls the overall operation of device 700, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 702 may include one or more modules to facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702.

[0120] Memory 704 is configured to store various types of data to support the operation of device 700. Examples of this data include instructions for any application or method operating on device 700, contact data, phonebook data, messages, pictures, videos, etc. Memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0121] Power supply component 706 provides power to various components of device 700. Power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 700.

[0122] Multimedia component 708 includes a screen that provides an output interface between the device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 708 includes a front-facing camera and / or a rear-facing camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0123] Audio component 710 is configured to output and / or input audio signals. For example, audio component 710 includes a microphone (MIC) configured to receive external audio signals when device 700 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 704 or transmitted via communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

[0124] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0125] Sensor assembly 714 includes one or more sensors for providing state assessments of various aspects of device 700. For example, sensor assembly 714 may detect the on / off state of device 700, the relative positioning of components such as the display and keypad of device 700, changes in the position of device 700 or a component of device 700, the presence or absence of user contact with device 700, the orientation or acceleration / deceleration of device 700, and temperature changes of device 700. Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0126] Communication component 716 is configured to facilitate wired or wireless communication between device 700 and other devices. Device 700 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 716 also includes a near-field communication (NFC) module to facilitate short-range communication.

[0127] In an exemplary embodiment, device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0128] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, which can be executed by a processor 720 of device 700 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0129] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0130] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A subscriber identification handling method, characterized by The method comprises: obtaining personal attribute information corresponding to a user identifier; the personal attribute information comprises a task sequence corresponding to the user identifier, an interaction state of each task in the task sequence, and user information, wherein the task sequence comprises at least one task, and the interaction state is an interaction state of a resource in a process of performing each task; inputting the personal attribute information into a user type identification model to identify a user type corresponding to the user identifier; the user type identification model is obtained by training historical personal attribute information of a sample user; when the user type is consistent with a preset type, starting a preset protection strategy for the user identifier; wherein the preset type is a user type with a proficiency less than a first preset threshold in completing the task, and the proficiency represents a proficiency of the user in completing the task; the obtaining of the personal attribute information corresponding to the user identifier comprises: detecting a number of tasks in the task sequence; when the number of tasks is less than a second preset threshold, obtaining the personal attribute information corresponding to the user identifier, wherein the number of tasks is a number of completed tasks in the task sequence.

2. The user identification processing method according to claim 1, characterized by, the preset protection strategy comprises a protection strategy of allocating a preset resource to a user corresponding to the preset type in a process of performing a task.

3. The user identification processing method according to claim 1, characterized by, the obtaining method of the user type identification model comprises: obtaining historical personal attribute information corresponding to the sample user; determining a user type corresponding to the user identifier according to the historical personal attribute information; training a preset initial identification model by taking the historical personal attribute information as input and taking the user type as supervision information to obtain the user type identification model.

4. The user identification processing method according to claim 3, characterized by, the determining of the user type corresponding to the user identifier according to the historical personal attribute information comprises: after completion of the at least one task, ending the task, and then determining the user type corresponding to the user identifier as a user type that needs to be protected; wherein the number of the at least one task is less than a third preset threshold.

5. The user identification processing method according to claim 3, characterized by, the user information in the historical personal attribute information comprises a login state corresponding to the user identifier; the determining of the user type corresponding to the user identifier according to the historical personal attribute information comprises: detecting the login state corresponding to the user identifier within a preset time period to obtain a login frequency of the user identifier; if the login frequency of the user identifier is less than a fourth preset threshold within the preset time period, determining the user type corresponding to the user identifier as a user type that needs to be protected.

6. The user identification processing method according to claim 3, characterized by, the interaction state in the historical personal attribute information comprises an interaction frequency in a process of performing each task; the determining of the user type corresponding to the user identifier according to the historical personal attribute information comprises: detecting the interaction frequency in the process of performing each task; if the interaction frequency in the process of performing each task is less than a fifth preset threshold, determining the user type corresponding to the user identifier as a user type that needs to be protected.

7. A user identification processing apparatus, characterized by comprising: The method comprises: The personal attribute information acquisition unit is configured to acquire personal attribute information corresponding to the user identifier, the personal attribute information including a task sequence corresponding to the user identifier, an interaction state of each task in the task sequence, and user information, wherein the task sequence includes at least one task, and the interaction state is an interaction state of a resource in a process of performing each task. The user type determination unit is configured to input the personal attribute information into a user type identification model to identify the user type of the user identifier, wherein the user type identification model is trained according to historical personal attribute information of a sample user. The user identifier processing unit is configured to start a preset protection strategy for the user identifier when the user type is consistent with a preset type, wherein the preset type is a user type with a proficiency less than a first preset threshold in completing the task, and the proficiency represents a proficiency of the user in completing the task. The personal attribute information acquisition unit is further configured to detect a number of tasks in the task sequence, and acquire personal attribute information corresponding to the user identifier when the number of tasks is less than a second preset threshold, wherein the number of tasks is a number of completed tasks in the task sequence.

8. The user identification processing apparatus according to claim 7, characterized by, The user identifier processing device further includes a protection strategy storage unit configured to store the preset protection strategy, wherein the preset protection strategy includes a protection strategy of allocating a preset resource to a user corresponding to the preset type in a process of performing a task.

9. The user identification processing apparatus according to claim 7, characterized by, The user type identification model determination unit is configured to: acquire historical personal attribute information corresponding to the sample user; determine a user type corresponding to the user identifier according to the historical personal attribute information; train a preset initial identification model by taking the historical personal attribute information as input and taking the user type as supervision information, to obtain the user type identification model.

10. The user identification processing apparatus according to claim 9, characterized by, The user type identification model determination unit is further configured to: determine the user type corresponding to the user identifier as a user type that needs to be protected after at least one task in the task sequence is completed, wherein the number of the at least one task is less than a third preset threshold.

11. The user identification processing apparatus according to claim 9, characterized by, The user information in the historical personal attribute information includes a login state corresponding to the user identifier. The user type identification model determination unit is further configured to: detect the login state corresponding to the user identifier within a preset time period to obtain a login frequency of the user identifier; determine the user type corresponding to the user identifier as a user type that needs to be protected if the login frequency of the user identifier is less than a fourth preset threshold within the preset time period.

12. The user identification processing apparatus according to claim 9, characterized by, The interaction state in the historical personal attribute information includes an interaction frequency in a process of performing each task. The user type identification model determination unit is further configured to: detect the interaction frequency in the process of performing each task. If the number of interactions in the process of performing each of the tasks is less than a fifth preset threshold, the user type corresponding to the user identifier is determined as a user type that needs to be protected.

13. An electronic device, comprising: Comprise: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the user identifier processing method of any one of claims 1-6.

14. A storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enable the electronic device to perform the user identifier processing method of any one of claims 1-6.

Images