A task push method, device and electronic device

Abstract

This specification discloses one or more embodiments of a task push method, apparatus, and electronic device. This solution categorizes the needs and / or statuses of selected users into multiple user groups. For a target user to whom a task is to be pushed, the corresponding user group can be determined based on the target user's basic data. Then, based on the determined user group and the target user's basic data, a target task matching the target user is selected from a preset task pool, along with target benefits bound to the target task. The target task is then sent to the target user for execution, and upon receiving the execution response, the target benefits are issued to the target user. This provides users with personalized tasks and benefits, improves task completion rates, and further enhances user activity and retention rates.

Description

Technical Field

[0001] This document relates to the field of computer software technology, and in particular to a task push method, device, and electronic device. Background Technology

[0002] With the rapid development of the Internet of Things (IoT), an increasing number of applications launched by e-commerce platforms or other online platforms have emerged. In order to achieve the platform's service goals and ensure user retention and growth, these applications often push promotional activities to users and guide them to complete daily tasks.

[0003] However, currently, the activities or tasks pushed are generally configured manually or uniformly according to rules. Therefore, the tasks or activities pushed to all users are the same, but because the target users are different, there may be tasks that are not what some users expect and cannot be accepted by most users, resulting in low task completion rate or poor completion effect, thereby reducing user activity and retention rate on the platform. Summary of the Invention

[0004] The purpose of one or more embodiments of this specification is to provide a task push method, apparatus, and electronic device to determine and push matching tasks to users based on their personalized needs, and to distribute rights and benefits matching the tasks to users after they complete the tasks, thereby providing users with personalized tasks and benefits, improving task completion rates, and further enhancing user activity and retention rates.

[0005] To solve the above-mentioned technical problems, one or more embodiments of this specification are implemented as follows:

[0006] Firstly, a task push method is proposed, including:

[0007] Based on the target user's basic data, user groups matching the target user are determined from multiple user groups, wherein each user group contains demand data representing the overall needs and / or status of users in that user group;

[0008] Based on the determined user group's demand data and the target user's basic data, a target task matching the target user is selected from a preset task pool, wherein the target task is bound to a corresponding target benefit;

[0009] The target task is pushed to the target user so that the target user can perform the target task;

[0010] After receiving a response indicating that the target task has been completed, the target benefits associated with the target task will be distributed to the target user.

[0011] Secondly, a task push device is proposed, comprising:

[0012] The determination module is used to determine the user group that matches the target user from multiple user groups based on the target user's basic data, wherein each user group contains demand data representing the overall needs and / or status of users in that user group;

[0013] The selection module is used to select a target task that matches the target user from a preset task pool based on the demand data of the determined user group and the basic data of the target user, wherein the target task is bound to a corresponding target benefit;

[0014] The push module is used to push the target task to the target user so that the target user can perform the target task;

[0015] The distribution module is used to distribute the target benefits bound to the target task to the target user after receiving the response returned by the completion of the target task.

[0016] Thirdly, an electronic device is proposed, comprising:

[0017] Processor; and

[0018] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the task push method described in the first aspect.

[0019] Fourthly, a computer-readable storage medium is proposed that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the task push method described in the first aspect.

[0020] As can be seen from the technical solutions provided in one or more embodiments of this specification above, based on the needs data of the selected users as the grouping basis, the needs of the target users—the objects of the push tasks—can be accurately located. Then, based on the determined needs and the target user's own basic data, suitable target tasks are further matched, thus achieving personalized task matching. Furthermore, since the target benefits are bound to the target tasks, after the target user completes the target task, the target benefits can be distributed to the target user through appropriate channels. This incentivizes target users to complete target tasks, increases user activity, guides rapid user growth, and enhances user stickiness and retention rates. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in one or more embodiments or prior art of this specification, the accompanying drawings used in the description of one or more embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the task push scheme provided in the embodiments of this specification in an advertising platform scenario.

[0023] Figure 2 This is a schematic diagram illustrating the steps of a task push method provided in the embodiments of this specification.

[0024] Figure 3 This is a schematic diagram illustrating a user's selection of categories, provided as an embodiment of this specification.

[0025] Figure 4 This is a schematic diagram of the task level distribution in a task pool provided in one embodiment of this specification.

[0026] Figure 5 This is a schematic diagram of the matching connection between a user and a task in the task pool through an online matching test, provided as an embodiment of this specification.

[0027] Figure 6 This is a flowchart illustrating the push task provided in the embodiments of this specification.

[0028] Figure 7 This is a schematic diagram of the structure of a task push device provided in the embodiments of this specification.

[0029] Figure 8 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this specification. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described one or more embodiments are only some embodiments of this specification, and not all embodiments. All other embodiments obtained by those skilled in the art based on one or more embodiments of this specification without creative effort should fall within the protection scope of this document.

[0031] Various commercial platforms frequently boost active users and user retention rates by pushing operational activities or a series of assigned tasks to users. For example, they might select a fixed group of users based on rules, push tasks or activities to them, and reward them with benefits after completing the corresponding tasks and actions. For instance, the "New Store Benefits" activity on XX advertising platform selects new merchants and issues coupons to incentivize them to advertise. Alternatively, during specific periods (such as major sales events or anniversaries), they might hold a series of online subsidy or incentive activities, where users can enjoy platform-issued coupons, traffic subsidies, and other rewards after meeting certain conditions.

[0032] Clearly, these operational activities typically only target users through simple rules, resulting in inaccurate matching between activities and users. This leads to low participation rates and poor retention rates. Furthermore, whether it's a short-term campaign or a mature user task product feature, these activities only target a specific stage in the user lifecycle to boost activity and efficiency, failing to consider the user's growth process from new to returning user. Consequently, the effects are short-lived, with users gradually churning after the campaign period ends. Moreover, after participating in related activities and tasks, users do not experience any improvement due to insufficient matching accuracy.

[0033] Therefore, the current task or activity push notifications are too simplistic and forceful, failing to accurately match users with suitable tasks or activities, thus reducing user activity and retention on the platform. To address this, this specification proposes a new task push notification scheme. The basic concept of this scheme is as follows: by classifying the needs and / or statuses of selected users' demand data to obtain multiple user groups, for the target user of the task to be pushed, the user group corresponding to the target user can be determined based on the target user's basic data. Then, based on the determined user group and the target user's basic data, a target task matching the target user can be selected from a preset task pool, and a target benefit bound to the target task can be selected. Finally, the target task is sent to the target user for execution, and upon receiving the returned execution response, the target benefit is issued to the target user. Therefore, based on the needs data of the selected users as the grouping basis, the needs of the target users of the push task can be accurately located. Then, based on the determined needs and the basic data of the target user, the target task suitable for the target user can be further matched. Thus, personalized task matching is achieved. In addition, since the target benefits are bound to the target task, the target benefits can be distributed to the target user through appropriate channels after the target user completes the target task.

[0034] Since the needs and / or status of target users may change at different stages, it can be guaranteed that the target tasks matched for different target users at different stages will be almost different, and the corresponding target benefits will also be different. However, the matched target tasks and target benefits will meet the needs and expectations of the target users. Therefore, the task push solution provided in this manual can improve the task completion rate, increase user activity and retention rate, thereby ensuring and meeting the platform's operational needs and development.

[0035] It should be noted that the embodiments in this specification are task push solutions, where the tasks can be understood as various activities, tasks, and related products launched during platform operation. The scenarios applicable to this task push solution include, but are not limited to, various internet scenarios such as advertising platforms, e-commerce platforms, search engine platforms, and information and video platforms.

[0036] Reference Figure 1 The diagram illustrates a task push solution provided in this specification within an advertising platform scenario, using the example of server 102 providing advertising delivery services to user terminal 104. Server 102 can be a hardware device or software device with certain computing and processing capabilities deployed by the advertising delivery service provider; for example, a computer, platform computer, cloud server, or other types of server. User terminal 104 can be a terminal device or a client installed on a terminal device provider, used to display and transmit service content to the service requester, facilitating the service requester to complete the corresponding service request on user terminal 104. The service requester can be an individual user or a store merchant.

[0037] In the actual process of advertising service interaction, in order to improve user activity and stickiness, the advertising service provider can use server 102 to match personalized target tasks and target benefits to the service requester on user terminal 104 based on the user group to which the service requester belongs and the service requester's current platform performance. The target task is then pushed to the service requester through user terminal 104. After the service requester completes the target task through user terminal 104, the advertising service provider will issue the target benefits to the service requester through server 102 as an incentive. This will improve the service requester's stickiness to the advertising service provider's operating platform (i.e., server 102) and online activity, thereby ensuring the sustainability and operational needs of the advertising service provider.

[0038] Reference Figure 2 The diagram shown is a step-by-step illustration of a task push method provided in an embodiment of this specification. It should be understood that the execution entity of this method can be... Figure 1 The server shown may include the following steps in its task push method:

[0039] Step 202: Based on the target user's basic data, determine the user group that matches the target user from multiple user groups, wherein each user group contains demand data representing the overall needs and / or status of users in that user group.

[0040] The multiple user groups involved can be determined as follows: First, basic data of multiple users is collected periodically, and the basic data includes at least historical behavior data; then, based on the historical behavior data in the basic data, the needs and / or states of the multiple users are selected and classified according to a specified algorithm to obtain multiple user groups, where each user group corresponds to its own demand data. This demand data can be consumption capacity, exposure capacity, delivery capacity, etc.

[0041] In the embodiments of this specification, because the form of each user's historical behavior data may be different, the needs and / or status that can be fed back may not necessarily be directly obtained from the historical behavior data. Therefore, the needs and / or status of the multiple users can be selected and classified according to one or more of the following specified algorithms to obtain multiple user groups:

[0042] The first method involves selecting users based on historical behavioral data in the basic data and setting task rules to identify the needs and / or states of the multiple users, and grouping the needs data of the selected users that reflect the same needs and / or states into the same user group.

[0043] The task rules can be set according to specific tasks and goals, such as new user retention improvement tasks and goals, target sensitivity improvement tasks and goals, etc. Multiple groups can be pre-established based on the task rules. Each user group uses the defined task rules as its needs and / or status. Then, according to these established task rules, various types of information reflecting needs and / or statuses extracted from historical behavioral data are summarized and analyzed to obtain the demand data for each user group. This demand data reflects the overall needs and / or status of users within that user group.

[0044] The second method involves using historical behavioral data from the basic data to predict the needs and / or states of users with predictive needs based on a prediction model, and then selecting users based on the predicted needs data, grouping the needs data of the selected users that reflect the same needs and / or states into the same user group.

[0045] Because some needs and / or states cannot be determined solely from historical behavioral data, they require prediction based on forecasting models using historical behavioral data. For example, a churn prediction model can be used to estimate the probability of user churn, or an activity prediction model can be used to estimate user activity. Users whose prediction results are similar or within the same range can be considered to have the same needs and / or states and can be grouped into the same user group.

[0046] The third method involves clustering the demand data of the multiple users based on the historical behavioral data in the basic data using a clustering algorithm to obtain multiple user groups, with each group having demand data that reflects the same demand and / or status.

[0047] This clustering method can be used when users are not grouped based on a single indicator or estimated value (demand and / or status). In a typical task system, users are grouped into several tiers based on the level and type of tasks in a preset task pool. The number of tiers is used as the number of cluster centers. Multidimensional features are extracted from various types of historical behavioral data to cluster users' needs and / or statuses. The clusters obtained after convergence are the user groups for each tier.

[0048] It should be understood that, in the embodiments of this specification, the basic data may include the user's basic attribute information and the user's historical behavior data. The historical behavior data covers a broad range of data, including: historical ad placement frequency, ad exposure, ad clicks, historical orders, operation logs, etc. This historical behavior data can be analyzed to determine the user's needs and preferences. The basic attribute information may include store information, warehouse location, reputation, etc., which can reflect the user's status. Therefore, by using the basic data that reflects the user's needs and / or status, especially the historical behavior data within the basic data, the needs and / or status of each user among multiple users can be analyzed. Then, by using a specified algorithm to aggregate and analyze these needs and / or statuses, the demand data reflecting the same needs and / or statuses can be grouped into a single user group, thus obtaining multiple user groups.

[0049] For details, please refer to Figure 3 As shown, multiple users can be pre-selected and categorized according to the above grouping method, such as... Figure 3The n user groups obtained are as follows: The first user group is selected based on the user's basic attributes, and the determined demand data reflecting the user's basic attributes includes: new / existing customer information, and advertising habit information (e.g., promotional / continuous / cyclical / trial). The second user group is selected based on the user's activity status, and the determined demand data reflecting the user's activity status includes: estimated active days, and predicted churn. The nth user group is selected based on user demand mining, and the determined demand data reflecting the user's current needs includes: target sensitivity, and demand magnitude assessment. In fact, Figure 3 This is merely an example illustrating one possible user grouping scenario. In actual task push solutions, multiple user groups can be obtained in advance by selecting multiple users, and it is not limited to this. Figure 3 The number can also include more user grouping information.

[0050] Therefore, by pre-selecting multiple user groups determined by the user, the needs of the target users of the push task can be identified first, that is, one or more user groups that the target user falls into, so as to quickly and accurately locate the needs and / or status of the target users, so as to facilitate subsequent task matching.

[0051] Step 204: Based on the determined user group's demand data and the target user's basic data, select a target task that matches the target user from the preset task pool, wherein the target task is bound to a corresponding target benefit.

[0052] In the embodiments of this specification, the preset task pool can be established in advance in the following way: First, a task template is created, which includes at least a task content item and an execution condition item; then, based on periodically collected historical behavior data, multiple task objectives are analyzed and determined; next, the task template is populated with tasks based on each task objective to establish a task pool containing multiple tasks; wherein, each task in the preset task pool is bound to a unique right, thereby ensuring that different users can obtain the same right after successfully executing the task.

[0053] It should be understood that after each task is generated, a unique task identifier, or task ID, is also generated. In fact, tasks in the preset task pool can be automatically generated through the three steps described above, or they can be created manually. Whether automatically or manually generated, the task content and execution conditions need to be flexibly determined based on the needs and / or status of each user group. For example, if historical behavior data of selected users shows that a certain type of user frequently clicked on coupon-grabbing activities, and the user group to which this type of user is selected has a demand level assessment, then a task optimization objective can be created based on a task template: a custom plan to promote collection and shopping cart spending greater than or equal to 100 yuan.

[0054] To encourage task completion, each task is associated with specific benefits. Benefits in the benefits pool can be created manually or flexibly adjusted based on matched tasks. The creation process can be tailored to different users' sensitivities to benefit types. Benefit types can include: coupons (discount coupons, red envelopes, etc.), special product feature benefits (access to advanced product features), and performance support benefits (accelerated traffic, etc.). Benefits in the pool can be continuously enriched and updated, with updates similar to the creation process. Additionally, tasks with low completion rates or poor performance can be removed from the pool.

[0055] Reference Figure 4 As shown, the preset task pool includes tasks at various levels, from basic to intermediate to advanced, with the task level increasing progressively as the user becomes more familiar with the platform. For example, there are multiple task types such as basic account setup, campaign setup, product functionality, and performance maintenance, each suitable for users with varying levels of platform familiarity. The preset task pool is continuously enriched and updated. Basic account setup is the basic level, while performance maintenance is the advanced level.

[0056] --Basic Account Setup: These tasks ensure users can run ads normally and are suitable for new customers, returning customers who haven't advertised in a while, and other users unfamiliar with the platform. These tasks include: topping up accounts, creating new active campaigns, and setting report metrics. By completing these tasks, users learn the most basic operations of display ad campaigns, ad groups, creatives, optimization goals, and bidding, allowing them to enter a normal competitive state.

[0057] --Targeting Setup Type: This type of task guides users to diversify their targeting based on different needs. It's suitable for users already familiar with basic targeting operations. Tasks include: selecting different optimization goals, creating a smart bidding plan, creating an automatic bidding plan, using smart targeting, using extended targeting, adopting bidding suggestions, and enabling plan cold start functionality. By completing these tasks, users can learn to rationally select plan settings at each stage based on their specific needs, achieving more efficient and precise targeting.

[0058] --Product Feature-Based Tasks: These tasks guide clients towards more convenient ad placement. They are suitable for clients already familiar with basic ad placement operations or those with needs for intelligent and convenient ad placement. Promoting a product feature is best done by first testing it with clients who already have a certain level of loyalty. This type of task includes: using the Manager Plan, using the Product Selection feature, and using the Potential Plan feature. By completing these tasks, clients can learn and try out the latest product features offered by the advertising platform, improving their efficiency in the plan setup phase, reducing trial-and-error costs, and enhancing advertising effectiveness through intelligent product placement.

[0059] --Performance Maintenance Type: These tasks incentivize clients to maintain a certain level of advertising performance, increasing client engagement and stickiness. They are suitable for clients who already have stable performance or a mature advertising methodology. Examples include: achieving m days of activity within n days, reaching x% of the spending percentage for a specific campaign, or spending x yuan over n consecutive days. These tasks will be rewarded with higher-level incentives to improve user retention rates and other metrics, increasing platform product usage and spending percentage.

[0060] Accordingly, regarding the benefits of completing tasks, three types of benefits can be set up according to different customer needs: coupon type, special permission type, and performance support type.

[0061] --Coupon type: Coupon-type benefits refer to discount coupons that can be used to offset user spending, such as a 50% off coupon for 188 yuan or a 10% off coupon for 200 yuan. These benefits are suitable for new users and users with relatively limited budgets. Of course, the coupon amount that incentivizes users to complete tasks will vary depending on the user type. Coupon-type benefits are directly issued to users through the task center after they complete the task.

[0062] --Special Permission Type: This type of benefit generally refers to certain advanced permissions, which are only applicable to select clients. Examples include permissions for manual ad placement and consultation, cost control plans for adding items to cart and favorites, and refined audience operations. This type of benefit is suitable for users with relatively high-level engagement, multiple target audience goals, and audience flow management needs. After a user completes the task, special permission-type benefits will be directly added to the corresponding benefit role list in the backend and issued.

[0063] --Performance-based support: Performance-based support refers to using technical means to help users gain more exposure, clicks, favorites, add-to-cart, or make purchases, and even to support a certain amount of user traffic, such as helping users gain up to 500 extra exposures or helping users achieve their first sale. This type of support is applicable to users at all stages, with different support goals matched according to the user's different status and performance.

[0064] In one possible matching operation, step 204, when selecting a target task matching the target user from a preset task pool based on the determined user group's demand data and the target user's basic data, can determine the task type and threshold parameters of the target task for the target user based on the determined user group's demand data and the target user's basic data; and select a matching target task from the preset task pool based on the target task's task type and threshold parameters.

[0065] In practice, the task type of the target task can be determined for the target user based on the needs and / or status reflected by the demand data of the determined user group; then, the threshold parameter of the target task can be determined for the target user based on the basic data of the target user and the determined task type of the target task.

[0066] Optionally, refer to Figure 5 As shown, considering the lack of historical data accumulation in the initial stage, a matching method based on preset matching rules can be adopted. Specifically, based on the user's basic attributes, online matching tests can be conducted with different tasks and benefits. During the matching test, a bipartite graph can be obtained. Based on offline data analysis, matching rules between different users and task benefits can be obtained. Finally, based on different activity objectives, matching relationships with strong positive correlation to user effects (such as...) are retained. Figure 5 Solid lines connect), removing insignificant or negatively correlated matches (such as...). Figure 5 (Connected by dashed lines), the preset matching rules can be obtained. Then, based on the needs and / or status reflected by the determined user group's demand data, at least one target task type that matches the user group's needs and / or status is selected from the preset matching rules.

[0067] After determining the task type of the target task, it is necessary to further set threshold parameters for the target task based on the target user's basic data. Specifically, based on the target user's basic data, historical behavioral data reflecting the target user's needs and / or preferences can be determined. Based on the historical behavioral data, a matching parameter level can be selected as the threshold parameter for the task corresponding to the currently determined task type. In this way, after the task type and threshold parameters are determined, a matching target task can be selected from a preset task pool based on these conditions.

[0068] It should be understood that in the preset task pool and the benefits pool, tasks are divided into multiple types, and each type corresponds to multiple tiers. The tier for each type is defined based on different threshold parameters. Similarly, the benefits in the benefits pool are also divided into multiple types, and each type corresponds to multiple tiers. Benefits also have threshold parameters, and the different tiers for each benefit are determined by different threshold parameters.

[0069] For example, if the task type is "Use the Butler Plan," the corresponding task can be set into 5 tiers. Each tier increases the duration of the Butler Plan by one day and costs 20 yuan more. Tier 1: Use the Butler Plan for 1 day, cost 50 yuan; Tier 2: Use the Butler Plan for 2 days, cost 70 yuan; Tier 3: Use the Butler Plan for 3 days, cost 90 yuan; Tier 4: Use the Butler Plan for 4 days, cost 110 yuan; Tier 5: Use the Butler Plan for 5 days, cost 130 yuan.

[0070] It should be understood that the threshold parameters of the task and the specific amount / quantity of benefits involved in the task creation can be personalized and matched according to the algorithm.

[0071] Another feasible matching operation, primarily targeting cases with historical matching relationships, employs a matching algorithm that calculates task matching degree using a predefined formula. This maximizes user retention while ensuring a certain task completion rate. Specifically, based on the determined user group's demand data and the target user's basic data, the probability of the target user completing each task in the preset task pool is calculated. Based on the target user's completion probability for each task, a task ranking score is calculated for each task after execution. Based on the task ranking scores of the tasks in the preset task pool, at least one target task type and threshold parameter are determined for the target user.

[0072] In the embodiments of this specification, the calculation of the probability of a user completing a certain task i is assumed to be related to the user's sensitivity to the rights and interests corresponding to the task, i.e., whether or not the user completes the task. i and the difficulty level of the task d i Regarding this, we need a matching function `complete`. i It can output the probability of the user completing the task:

[0073] complete i =f(s) i ,d i ,θ)

[0074] Where s i The relationship between configuration benefits and user performance can be measured using parameters such as the relationship between benefits and user performance. For example, if the benefit is a 100 yuan red envelope, the user's sensitivity to the benefit can be simply measured by the proportion of 100 yuan to the user's average daily spending or the proportion to the amount of red envelopes the user has received in historical activities; i The difference between the task threshold and the user's current status can be used to measure this. For example, a 7-day valid task requires accumulating 50 yuan in spending. Judging from the user's current spending level, the difference between the amount the user's automatic bidding plan can spend by the task's end date and the threshold is the largest difference, indicating that the task is more difficult for the user to complete.

[0075] After determining the probability of the target user completing each task, the task ranking score after the task is executed can be calculated separately for each task. The task ranking score for each task is the sum of the product of the influencing factor controlling the completion rate of the task and the difference between the average completion rate of the task and the probability that the target user refuses to complete the task, and the improvement value of the task on the target task. The probability that the target user refuses to complete the task is 1 minus the probability that the target user completes the task.

[0076] The specific task ranking score after each task i is executed can be determined by referring to the following formula:

[0077] RankScore i =uplift i +β(M-refuse i ) = uplift i +β(M-1+complete i )

[0078] Among them, uplift i Let β be the improvement value of task i for the user. This improvement value can be set based on basic data, for example, the expected improvement value is 20% of the original value, that is, the improvement value is increased by 20%; β is the influencing factor controlling the completion rate of task i, and M is the average task completion rate of task i. i This represents the probability that the target user will refuse to complete the task. It should be noted that the uplift involved in the above formula... i and complete i All of these can be obtained through analysis of the target users' basic data.

[0079] After calculating the task ranking score for each task in the preset task pool according to the above formula, the top-ranked tasks can be selected as target tasks based on the target user's needs (previously interested in 2-3 tasks simultaneously) or a locally set threshold. Since all tasks are considered during the task ranking score calculation, the determined target tasks already include the threshold parameter, eliminating the need to set it again. This method of determining target tasks results in faster and more accurate matching.

[0080] It should be understood that since tasks and rights are linked, once the target tasks are determined, the target rights are also determined accordingly.

[0081] Step 206: Push the target task to the target user so that the target user can execute the target task.

[0082] Since there may be one or more target tasks matched, these target tasks can be pushed to the target users in batches or stages, or pushed in a timely manner in different scenarios, so that the target users can receive and execute the target tasks in a timely manner.

[0083] Step 208: After receiving the response indicating completion of the target task, the target benefits bound to the target task are distributed to the target user.

[0084] After users complete tasks, coupons and special product features can be directly issued to customers through backend configuration. Performance-based incentives, on the other hand, are processed by sending the list of users who have completed tasks to the platform, which then accelerates their effectiveness.

[0085] Reference Figure 6 The diagram shown is a flowchart of the push task provided in the embodiments of this specification.

[0086] First, based on multiple pre-established user groups, the target users are precisely segmented and positioned to determine the correct user group. If the target user is already selected, the search can be performed directly from the historical selection records. If the target user is a new user, the corresponding user group is determined based on the target user's basic data. After determining the target user group, the most suitable target tasks and benefits for the current stage can be matched from the task pool and benefit pool based on the target user's needs and / or user status, combined with the product feature promotion requirements of the server (e.g., the advertising service provider). Figure 6 As shown, the task pool includes at least several types of tasks: account setup tasks such as recharge and creating effective plans; product function tasks such as the Butler Plan and Product Selection; and performance maintenance tasks such as continuous activity and cumulative spending of n yuan. It also lists several types of benefits in the benefits pool: performance support benefits, cash coupons / vouchers, and special benefits. Finally, the matched target tasks are pushed to the target users for execution, and after the target users successfully complete the tasks, the benefits are distributed to them through various channels. For example, benefits can be distributed through end-to-end support, traffic incentives, or coupons / cards.

[0087] Therefore, by using user grouping-based needs and / or status, along with target user data, suitable target tasks can be quickly and accurately matched from a pre-set task pool, while simultaneously determining target benefits. This enables personalized task and benefit matching services for target users, increasing their acceptance of the target tasks. After pushing the target task to the target user and ensuring successful completion, target benefits are awarded, incentivizing them to complete the task, guiding them to quickly familiarize themselves with the platform, supporting their growth, and enhancing their self-operation capabilities. Furthermore, as users complete tasks and grow, their activity and spending power increase, contributing to platform revenue growth. The personalized task distribution and benefit matching system can also serve as an efficient promotion center for product features, technical means, and operational activities. Through benefit incentives, it can accurately and quickly promote the platform's high-quality capabilities and can be widely used by product, operations, and R&D departments.

[0088] Reference Figure 7 As shown, this is a task push device provided in an embodiment of this specification. The device 700 may include:

[0089] The determination module 702 is used to determine the user group that matches the target user from multiple user groups based on the target user's basic data, wherein each user group in the multiple user groups contains demand data representing the overall needs and / or status of users in that user group;

[0090] Selection module 704 is used to select a target task matching the target user from a preset task pool based on the determined demand data of the user group and the basic data of the target user, wherein the target task is bound to a corresponding target benefit;

[0091] The push module 706 is used to push the target task to the target user so that the target user can perform the target task.

[0092] The distribution module 708 is used to distribute the target rights bound to the target task to the target user after receiving the response returned by the completion of the target task.

[0093] Optionally, as an embodiment, the device 700 further includes: a collection module and a grouping module; the plurality of user groups are determined in the following manner:

[0094] The collection module is used to periodically collect basic data from multiple users, and the basic data includes at least historical behavior data.

[0095] The grouping module is used to select and classify the needs and / or status of the multiple users based on the historical behavior data in the basic data and a specified algorithm to obtain multiple user groups, wherein each user group corresponds to its own demand data.

[0096] In one specific implementation of an embodiment of this specification, when the grouping module obtains multiple user groups by selecting and classifying the needs and / or states of the multiple users based on historical behavioral data in the basic data and a specified algorithm, it is specifically used for:

[0097] Based on the historical behavior data in the basic data, users are selected according to the needs and / or status of the multiple users based on the set task rules, and the demand data of the selected users that can reflect the same needs and / or status are divided into the same user group; and / or;

[0098] Based on the historical behavioral data in the aforementioned basic data, the needs and / or states of users with predictive needs are predicted using a prediction model, and users are selected based on the predicted needs data. The needs data of the selected users that reflect the same needs and / or states are grouped into the same user group; and / or;

[0099] Based on the historical behavior data in the basic data, the demand data of the multiple users are clustered using a clustering algorithm to obtain multiple user groups, each group having demand data reflecting the same demand and / or status.

[0100] In another specific implementation of the embodiments of this specification, the preset task pool is established in the following manner:

[0101] Create a task template, which includes at least a task content item and an execution condition item; analyze and determine multiple task objectives based on periodically collected historical behavior data; populate the task template with tasks based on each task objective to establish a task pool containing multiple tasks; wherein each task in the preset task pool is bound to a unique right.

[0102] In another specific implementation of the embodiments of this specification, when the selection module 704 selects a target task matching the target user from a preset task pool based on the determined user group's demand data and the target user's basic data, it is specifically used for:

[0103] Based on the determined user group's demand data and the target user's basic data, the task type and threshold parameters of the target task are determined for the target user; based on the target task's task type and threshold parameters, a matching target task is selected from a preset task pool.

[0104] In another specific implementation of the embodiments of this specification, when the selection module 704 determines the task type and threshold parameters of the target task for the target user based on the determined demand data of the user group and the basic data of the target user, it is specifically used for:

[0105] Based on the needs and / or status reflected by the demand data of the determined user groups, the task type of the target task is determined for the target user; based on the basic data of the target user and the determined task type of the target task, the threshold parameter of the target task is determined for the target user.

[0106] In another specific implementation of the embodiments of this specification, when the selection module 704 determines the task type of the target task for the target user based on the needs and / or status reflected in the determined user group's demand data, it is specifically used for:

[0107] Based on the needs and / or status reflected by the determined user group's demand data, at least one target task type that matches the user group's needs and / or status is selected from preset matching rules; wherein, the preset matching rules are obtained by online testing and matching multiple users with multiple tasks in a preset task pool.

[0108] In another specific implementation of the embodiments of this specification, when the selection module 704 determines the threshold parameter of the target task for the target user based on the target user's basic data and the determined task type of the target task, it is specifically used for:

[0109] Based on the target user's basic data, determine historical behavioral data reflecting the target user's needs and / or preferences; based on the historical behavioral data, select a matching parameter level for the task corresponding to the currently determined task type as the threshold parameter for the target task.

[0110] In another specific implementation of the embodiments of this specification, when the selection module 704 determines the task type and threshold parameters of the target task for the target user based on the determined demand data of the user group and the basic data of the target user, it is specifically used for:

[0111] Based on the determined user group's demand data and the target user's basic data, calculate the target user's completion probability for each task in the preset task pool; based on the target user's completion probability for each task, calculate the task ranking score after each task is executed; and based on the task ranking scores of the tasks in the preset task pool, determine at least one target task's task type and threshold parameter for the target user.

[0112] In another specific implementation of the embodiments of this specification, when the selection module 704 calculates the task ranking score after each task is executed based on the completion probability of the target user for each task, it is specifically used for:

[0113] For each task, calculate the task ranking score after the task is executed; the task ranking score for each task is the sum of the product of the influencing factor controlling the completion rate of the task and the difference between the average completion rate of the task and the probability that the target user refuses to complete the task, and the improvement effect value of the task on the target task; wherein, the probability that the target user refuses to complete the task is 1 minus the probability that the target user completes the task.

[0114] In another specific implementation of the embodiments of this specification, the preset task pool contains multiple levels of task ladders, each task ladder has multiple task types, and the task set corresponding to each task type contains tasks with multiple parameter levels.

[0115] By categorizing the needs and / or statuses of selected users, multiple user groups are obtained. For the target user of the task to be pushed to, the user group corresponding to the target user can be determined from the selected user groups based on the target user's basic data. Then, based on the needs data of the determined user group and the target user's basic data, a target task matching the target user can be selected from a preset task pool, along with the target benefits bound to that task. The target task is then sent to the target user for execution, and upon receiving the execution response, the target benefits are issued to the target user. Thus, by using the needs data of the selected users as the grouping basis, the needs of the target users can be accurately identified. Then, based on the determined needs and the target user's own basic data, a suitable target task can be further matched, thereby achieving personalized task matching. Furthermore, since the target benefits are bound to the target task, after the target user completes the target task, the target benefits can be issued to the target user through appropriate channels. This incentivizes target users to complete target tasks, guides user growth, and enhances user stickiness and retention.

[0116] Figure 8 This is a schematic diagram of the structure of an electronic device according to one embodiment of this specification. Please refer to it. Figure 8At the hardware level, the electronic device includes a processor, and optionally also an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include hardware required for other services.

[0117] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0118] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0119] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a task delivery mechanism at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0120] Based on the target user's basic data, user groups matching the target user are determined from multiple user groups, wherein each user group contains demand data representing the overall needs and / or status of users in that user group; based on the determined user group's demand data and the target user's basic data, a target task matching the target user is selected from a preset task pool, wherein the target task is bound to corresponding target benefits; the target task is pushed to the target user so that the target user can execute the target task; after receiving a response indicating completion of the target task, the target benefits bound to the target task are distributed to the target user.

[0121] The above is as described in this instruction manual. Figure 2The methods performed by the apparatus disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in one or more embodiments of this specification. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in one or more embodiments of this specification can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0122] The electronic device can also perform Figure 2 The method, and implement the corresponding device in Figure 2 The functions of the embodiments shown are not described in detail here.

[0123] Of course, in addition to the software implementation, the electronic devices in the embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0124] This specification also provides an embodiment of a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 2 The method of the illustrated embodiment is specifically used to perform the following method:

[0125] Based on the target user's basic data, user groups matching the target user are determined from multiple user groups, wherein each user group contains demand data representing the overall needs and / or status of users in that user group; based on the determined user group's demand data and the target user's basic data, a target task matching the target user is selected from a preset task pool, wherein the target task is bound to corresponding target benefits; the target task is pushed to the target user so that the target user can execute the target task; after receiving a response indicating completion of the target task, the target benefits bound to the target task are distributed to the target user.

[0126] In summary, the above description is merely a preferred embodiment of this specification and is not intended to limit the scope of protection of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

[0127] The systems, apparatuses, modules, or units described in one or more of the above embodiments may be implemented by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, a computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0128] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0130] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0131] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

Claims

1. A task pushing method, comprising: determining a user group matching a target user from a plurality of user groups based on collected basic data of the target user, wherein the basic data at least contains historical behavior data, and each user group of the plurality of user groups contains demand data representing the overall demand and / or state of users in the user group; calculating a completion probability of each task in a preset task pool by the target user based on the demand data of the determined user group and the basic data of the target user, wherein the completion probability of each task by the target user is calculated according to the task difficulty and benefit sensitivity of each task; calculating a task ranking score of each task after the task is executed according to the completion probability of each task by the target user; selecting at least one task with a high ranking as a target task, the target task being bound to a corresponding target benefit; pushing the target task to the target user to facilitate the target user to execute the target task; after receiving a response returned by completing the target task, issuing the target benefit bound to the target task to the target user. 2.The task pushing method of claim 1, wherein the plurality of user groups are determined by: periodically collecting basic data of a plurality of users; According to the historical behavior data in the basic data, the needs and / or states of the plurality of users are classified into a plurality of user groups based on a specified algorithm, wherein each user group corresponding to respective demand data. 3.The task pushing method of claim 2, wherein the plurality of user groups are obtained by classifying the demand and / or state of the plurality of users based on a specified algorithm according to the historical behavior data in the basic data, comprising: classifying the demand and / or state of the plurality of users based on a set task rule according to the historical behavior data in the basic data, and dividing the demand data of the classified users reflecting the same demand and / or state into the same user group; and / or; predicting the demand and / or state of users with predicted demand based on a prediction model according to the historical behavior data in the basic data, and classifying the users according to the predicted demand data, and dividing the demand data of the classified users reflecting the same demand and / or state into the same user group; and / or; obtaining the plurality of user groups by clustering the demand data of the plurality of users based on a clustering algorithm according to the historical behavior data in the basic data, each group having demand data reflecting the same demand and / or state. 4.The task pushing method of any one of claims 1-3, wherein the preset task pool is established by: creating a task template, the task template at least containing a task content item and an execution condition item; analyzing and determining a plurality of task objectives according to periodically collected historical behavior data; establishing a task pool containing a plurality of tasks by task filling the task template based on each task objective; wherein each task in the preset task pool is bound to a unique benefit. 5.The task pushing method of claim 1, further comprising: determining a task type of the target task for the target user based on the demand and / or state reflected by the demand data of the determined user group. According to the basic data of the target user and the determined task type of the target task, a threshold parameter of the target task is determined for the target user.

6. The task pushing method of claim 5, wherein the task type of the target task is determined for the target user based on the demand and / or state reflected by the determined demand data of the user group, comprising: selecting at least one task type of the target task matching the demand and / or state of the user group from preset matching rules based on the demand and / or state reflected by the determined demand data of the user group; wherein the preset matching rules are obtained by online test matching of a plurality of users and a plurality of tasks in a preset task pool.

7. The task pushing method of claim 5, wherein the threshold parameter of the target task is determined for the target user according to the basic data of the target user and the determined task type of the target task, comprising: determining historical behavior data reflecting the demand and / or preference of the target user according to the basic data of the target user; selecting a matching parameter gear corresponding to the task of the current determined task type as the threshold parameter of the target task according to the historical behavior data.

8. The task pushing method of claim 1, wherein the task ranking score of each task after being executed is calculated based on the completion probability of the target user for each task, comprising: calculating the task ranking score of each task after being executed respectively; the task ranking score of each task is the sum of the product of the influence factor of the control of the completion rate of the task and the difference between the average completion rate of the task and the probability of the target user refusing to complete the task, and the effect improvement value of the task to the target task; wherein the probability of the target user refusing to complete the task is 1 minus the completion probability of the target user for the task.

9. The task pushing method of any one of claims 1-3, 5-7, wherein the preset task pool comprises a plurality of task ladder levels, each task ladder level is provided with a plurality of task types, and each task type corresponds to a task set comprising a plurality of parameter gear tasks.

10. A task pushing device, comprising: a determination module configured to determine a user group matching the target user based on collected basic data of the target user, wherein the basic data at least comprises historical behavior data, and each user group in the plurality of user groups comprises demand data representing the overall demand and / or state of the users in the user group; a selection module configured to calculate the completion probability of the target user for each task in a preset task pool based on the demand data of the determined user group and the basic data of the target user; wherein the completion probability of the target user for each task is calculated according to the task difficulty and benefit sensitivity of each task; the task ranking score of each task after being executed is calculated according to the completion probability of the target user for each task; at least one task with a high ranking is selected as a target task, and the target task is bound with a corresponding target benefit. The push module is configured to push the target task to the target user so as to perform the target task by the target user. The issue module is configured to issue a target benefit bound with the target task to the target user after receiving a response returned by completing the target task. 11.An electronic device comprising: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the task pushing method of any one of claims 1-9. 12.A computer readable storage medium storing one or more programs, which, when executed by an electronic device comprising a plurality of applications, cause the electronic device to perform the task pushing method of any one of claims 1-9.

Images