Marketing methods, apparatuses, media, and computing devices

Abstract

Embodiments of the present application provide a marketing method, device, medium and computing device, which are applied to a marketing platform; the method comprises: in response to a triggering operation of a target user for a marketing activity, obtaining user feature data of the target user; based on the user feature data of the target user, determining a marketing task matched with the user feature data from a marketing task candidate pool corresponding to the marketing platform; wherein the marketing task comprises a behavior performance task and a behavior performance reward; assigning the marketing task to the target user, so that the target user performs the behavior performance task, and after the target user performs the behavior performance task, issuing the behavior performance reward to the target user, so that the target user claims the behavior performance reward; based on a task execution result and a reward claiming result corresponding to the target user, updating the user feature data of the target user. The present application can realize personalized marketing for users and improve marketing effect.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer application technology, and more specifically, the embodiments of the present invention relate to a marketing method, apparatus, medium and computing device. Background Technology

[0002] This section is intended to provide background or context for embodiments of the invention as set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] With the development of internet technology, the number and variety of internet products are increasing. Internet products can provide specific services to users through the internet; for example, video websites or apps can provide users with online video playback services, music apps can provide users with online music playback services, shopping apps can provide users with online shopping services, and so on.

[0004] For internet products, marketing to users via the internet is a crucial part of their operation. Through targeted marketing strategies, internet products can typically achieve business metrics set according to actual needs. These metrics can include GMV (Gross Merchandise Volume), active users, new customer acquisition, and order growth. Therefore, internet product operators usually invest significant financial, human, and material resources in their marketing efforts.

[0005] However, an inappropriate marketing strategy can prevent internet products from achieving their business targets, wasting the resources invested by the product's operators. Therefore, determining the right marketing strategy to improve marketing effectiveness and reduce resource consumption is a crucial issue for the operation of internet products. Summary of the Invention

[0006] In this context, embodiments of the present invention are intended to provide a marketing method, apparatus, medium, and computing device.

[0007] In a first aspect of the present invention, a marketing method is provided, applied to a marketing platform; the method includes:

[0008] In response to a target user's triggered action in relation to a marketing campaign, the user characteristic data of the target user is obtained;

[0009] Based on the user characteristic data of the target user, marketing tasks that match the user characteristic data are determined from the marketing task candidate pool corresponding to the marketing platform; wherein, the marketing tasks include behavioral fulfillment tasks and behavioral fulfillment rewards;

[0010] The marketing task is assigned to the target user so that the target user performs the behavioral fulfillment task, and after the target user completes the behavioral fulfillment task, the behavioral fulfillment reward is issued to the target user so that the target user can claim the behavioral fulfillment reward;

[0011] Based on the task execution results and reward redemption results corresponding to the target user, update the user characteristic data of the target user.

[0012] In a second aspect of the present invention, a marketing device is provided, applied to a marketing platform; the device includes:

[0013] The acquisition module is used to acquire user characteristic data of the target user in response to the target user's triggered operation for the marketing campaign;

[0014] The first determining module is used to determine marketing tasks that match the user characteristic data from the marketing task candidate pool corresponding to the marketing platform based on the user characteristic data of the target user; wherein, the marketing task includes behavioral fulfillment tasks and behavioral fulfillment rewards;

[0015] The allocation module is used to allocate the marketing task to the target user so that the target user can perform the behavioral fulfillment task, and after the target user has completed the behavioral fulfillment task, to issue the behavioral fulfillment reward to the target user so that the target user can claim the behavioral fulfillment reward;

[0016] The update module is used to update the user characteristic data of the target user based on the task execution results and reward claim results corresponding to the target user.

[0017] In a third aspect of the present invention, a medium is provided having a computer program stored thereon, which, when executed by a processor, implements any of the marketing methods described above.

[0018] In a fourth aspect of the present invention, a computing device is provided, comprising:

[0019] processor;

[0020] Memory used to store processor-executable programs;

[0021] The processor implements any of the marketing methods described above by running the executable program.

[0022] According to an embodiment of the present invention, a marketing platform can respond to a user's triggered operation for a marketing activity, obtain the user's user characteristic data, determine a marketing task matching the user's user characteristic data from a marketing candidate pool corresponding to the marketing platform, and then assign the marketing task to the user, enabling the user to perform the behavioral fulfillment task within the marketing task. After the user completes the behavioral fulfillment task, the user is issued a behavioral fulfillment reward for the marketing task, allowing the user to claim the behavioral fulfillment reward. Finally, the user's user characteristic data can be updated based on the task execution result and reward claim result corresponding to the user.

[0023] The above approach offers several advantages. First, it transforms marketing campaigns into marketing tasks. When a user triggers a campaign, a matching task can be assigned from a pool of potential users, rather than directly delivering the campaign. Therefore, when marketing strategies change, only the assigned task needs to be modified, or the task itself only slightly altered, reducing costs and improving timeliness. Second, based on user characteristic data, marketing tasks matching the user's data are assigned, enabling personalized marketing. Third, after a user completes a marketing task and claims its reward, their user characteristic data is updated. This allows for subsequent matching tasks based on the updated data, introducing user data feedback and improving marketing effectiveness. Attached Figure Description

[0024] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated in the drawings by way of example and not limitation, wherein:

[0025] Figure 1 A schematic diagram illustrating a marketing scenario according to an embodiment of the present invention is shown.

[0026] Figure 2 A flowchart illustrating a marketing method according to an embodiment of the present invention is shown schematically;

[0027] Figure 3 A schematic diagram of a page according to an embodiment of the present invention is shown;

[0028] Figure 4A schematic diagram of another page according to an embodiment of the present invention is shown;

[0029] Figure 5 A schematic diagram illustrating a process for determining a marketing task according to an embodiment of the present invention is shown.

[0030] Figure 6 A schematic diagram illustrating another marketing task determination process according to an embodiment of the present invention is shown.

[0031] Figure 7 A schematic diagram of a medium according to an embodiment of the present invention is shown;

[0032] Figure 8 A block diagram of a marketing device according to an embodiment of the present invention is shown schematically;

[0033] Figure 9 A schematic diagram of a computing device according to an embodiment of the present invention is shown.

[0034] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0035] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make the invention more thorough and complete, and to fully convey the scope of the invention to those skilled in the art.

[0036] Those skilled in the art will understand that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0037] According to embodiments of the present invention, a marketing method, apparatus, medium, and computing device are proposed.

[0038] In this article, it is important to understand that any number of elements in the accompanying figures is for illustrative purposes and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0039] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments. Invention Overview

[0041] In related technologies, when marketing internet products to users, one approach is for the internet product's operator to set up various marketing activities. Each marketing activity can serve as a marketing strategy, fulfilling one or more business needs. Users' participation in these marketing activities helps the internet product achieve corresponding business metrics.

[0042] However, in this approach, each marketing campaign is typically developed based on specific needs and remains fixed. Because each campaign requires significant resource investment across front-end, back-end, testing, product, operations, and maintenance, and necessitates reassessment and modification of campaigns when marketing strategies change, marketing costs are high and timeliness is poor. Furthermore, since each campaign is usually developed for a specific user group to attract a wider audience, personalized marketing cannot be achieved.

[0043] Another approach is for the operator of the internet product to select specific users and offer them prizes as a marketing strategy to encourage them to use the product.

[0044] However, this approach lacks guidance on user behavior and cannot guarantee that users will use the internet product after receiving the prize, making it difficult for the product to achieve its business metrics. Furthermore, the lack of user data feedback makes it impossible to optimize the selected users for prize distribution, resulting in poor marketing effectiveness and hindering personalized marketing.

[0045] This invention provides a marketing technical solution in which a marketing platform responds to a user's triggered operation for a marketing activity, obtains the user's user characteristic data, determines a marketing task matching the user's user characteristic data from a marketing candidate pool corresponding to the marketing platform, assigns the marketing task to the user, allowing the user to perform the behavioral fulfillment task within the marketing task, and issues the behavioral fulfillment reward to the user after the user completes the behavioral fulfillment task, allowing the user to claim the behavioral fulfillment reward. Finally, the user's user characteristic data is updated based on the task execution result and reward claim result corresponding to the user.

[0046] The above approach offers several advantages. First, it transforms marketing campaigns into marketing tasks. When a user triggers a campaign, a matching task can be assigned from a pool of potential users, rather than directly delivering the campaign. Therefore, when marketing strategies change, only the assigned task needs to be modified, or the task itself only slightly altered, reducing costs and improving timeliness. Second, based on user characteristic data, marketing tasks matching the user's data are assigned, enabling personalized marketing. Third, after a user completes a marketing task and claims its reward, their user characteristic data is updated. This allows for subsequent matching tasks based on the updated data, introducing user data feedback and improving marketing effectiveness.

[0047] After introducing the basic principles of the present invention, various non-limiting embodiments of the present invention will be described in detail below.

[0048] Application Scenarios Overview

[0049] refer to Figure 1 , Figure 1 A schematic diagram illustrating a marketing scenario according to an embodiment of the present invention is shown.

[0050] like Figure 1 As shown, in a marketing scenario, it may include a marketing platform and at least one client (e.g., client 1-N) that accesses the marketing platform via any type of wired or wireless network.

[0051] The aforementioned marketing platform can be deployed on a server containing a single physical host or a server cluster consisting of multiple independent physical hosts; alternatively, the aforementioned marketing platform can be a server-side application built on cloud computing services.

[0052] The aforementioned client can correspond to an APP installed by the user on their electronic device; specifically, the electronic device can be a smartphone, tablet, laptop, PC (Personal Computer), PDA (Personal Digital Assistant), wearable device (e.g., smart glasses, smartwatch), smart in-vehicle device, or game console, etc.

[0053] The aforementioned marketing platform can deliver marketing campaigns to users through the aforementioned client, allowing users to participate in the campaigns on the client. Upon completion of the campaign, the marketing platform can distribute corresponding rewards to users through the client, enabling users to claim and use the rewards on the client. Furthermore, the client can provide feedback to the marketing platform regarding the user's performance in the marketing campaign and the receipt of the reward.

[0054] In practice, the aforementioned marketing platform can respond to any user's (which may be referred to as the target user) triggered action in response to a marketing campaign and obtain the user characteristic data of that target user.

[0055] Once the aforementioned marketing platform obtains the user characteristic data of the target users, it can determine the marketing tasks that match the user characteristic data from the marketing task candidate pool corresponding to the marketing platform.

[0056] Once the marketing platform identifies a marketing task that matches the user characteristic data of the target user, it can assign the marketing task to that target user, enabling the target user to perform the behavioral fulfillment task within the marketing task. Subsequently, upon completion of the behavioral fulfillment task, the marketing platform can issue a behavioral fulfillment reward to the target user, allowing the target user to claim the reward.

[0057] The aforementioned marketing platform can further update the target user's user characteristic data based on the task execution results and reward redemption results. In this case, the marketing platform can then assign marketing tasks to the target user that match the target user's updated user characteristic data.

[0058] Exemplary methods

[0059] The following is combined with Figure 1 Application scenarios, refer to Figures 2-6 This description illustrates a marketing method according to exemplary embodiments of the present invention. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of the invention, and the embodiments of the invention are not limited in any way. Rather, the embodiments of the invention can be applied to any applicable scenario.

[0060] refer to Figure 2 , Figure 2 A flowchart illustrating a marketing method according to an embodiment of the present invention is shown schematically.

[0061] The above marketing methods can be applied to, for example Figure 1The marketing platform shown corresponds to a marketing task candidate pool. Specifically, the marketing task candidate pool can be stored locally on the marketing platform or on other devices connected to the marketing platform, allowing the marketing platform to access the marketing task candidate pool and retrieve marketing tasks from it. The operator corresponding to the marketing activity (e.g., the operator of the internet product providing the marketing activity to users) can perform operations such as adding, deleting, modifying, backing up, and restoring marketing tasks from the marketing task candidate pool.

[0062] In practical applications, the marketing task candidate pool can include multiple marketing tasks, and one or more marketing tasks can form a marketing campaign.

[0063] The above marketing methods may include the following steps:

[0064] Step 201: In response to the target user's triggered action on the marketing campaign, obtain the user characteristic data of the target user.

[0065] In this embodiment, for any user (referred to as a target user), when participating in a marketing activity, the target user can first perform a trigger operation for the marketing activity. The marketing platform can then respond to the target user's trigger operation for the marketing activity and obtain the target user's user characteristic data.

[0066] Specifically, the aforementioned marketing platform can deliver the marketing campaign to the target user through a client application corresponding to that target user, enabling the target user to participate in the campaign on that client application. This client application can be installed on the target user's electronic device, or it can be a client logged into using the target user's account, etc.

[0067] Accordingly, when the target user participates in the aforementioned marketing activity, they can first trigger the activity through the client. Upon detecting this trigger, the client can send a notification message to the marketing platform instructing the target user to participate. Upon receiving this notification message, the marketing platform can determine the target user's participation and thus obtain their user characteristic data.

[0068] In some embodiments, the target user's triggering action for the marketing campaign may include: the target user's triggering action for interactive controls in a user-facing page related to the marketing campaign.

[0069] For example Figure 3Taking the page shown as an example, this page could specifically be a "Claim Red Envelope" marketing campaign page; the interactive controls on this page could include a square "Claim Red Envelope" button. The aforementioned marketing platform can output this page to the target user through a client corresponding to the target user. When the target user participates in the marketing campaign, they can click the button, i.e., perform a click operation on the button; at this time, the target user's click operation on the button can be regarded as the target user's trigger operation for the marketing campaign.

[0070] And so on Figure 4 Taking the page shown as an example, this page could specifically be a product promotion page; the interactive controls on this page could include a circular "Claim Coupon" button. The aforementioned marketing platform can output this page to the target user through a client corresponding to the target user. The target user can view and purchase promotional products through this page, and when participating in the coupon-claiming marketing activity, they can click the button, i.e., perform a click operation on the button; at this time, the target user's click operation on the button can be regarded as the target user's trigger operation for the marketing activity.

[0071] Step 202: Based on the user characteristic data of the target user, determine the marketing task that matches the user characteristic data from the marketing task candidate pool; wherein, the marketing task includes behavioral fulfillment task and behavioral fulfillment reward.

[0072] In this embodiment, when the marketing platform obtains the user characteristic data of the target user, it can determine the marketing task that matches the user characteristic data from the marketing task candidate pool based on the user characteristic data. At this time, the marketing task can be regarded as a marketing task suitable for the target user. That is, it can be considered that the target user has a high willingness to perform the marketing task.

[0073] In practical applications, the aforementioned marketing tasks can include behavioral fulfillment tasks and behavioral fulfillment rewards. The behavioral fulfillment task can be a task that restricts the specific content and number of times a user's behavior can be performed; for example, a user completing their first payment on the app, a user browsing a promotional page for more than 10 seconds, a user liking or commenting on a popular influencer's post, etc. The behavioral fulfillment reward can be a reward issued to the user after completing the behavioral fulfillment task; for example, a 10 yuan no-threshold red envelope, a random red envelope with an amount in the range [1, 100], or a product that has just been discounted in the user's browsing history, etc.

[0074] In some embodiments, different marketing task candidate pools can be set up according to different marketing objectives (e.g., business metrics to be achieved through marketing strategies); that is, the marketing platform described above can correspond to multiple marketing task candidate pools, and different marketing task candidate pools in these multiple marketing task candidate pools correspond to different marketing objectives.

[0075] In the above scenario, when the marketing platform determines marketing tasks matching the target user's user characteristic data from its corresponding marketing task candidate pool, it can first determine the marketing task candidate pool corresponding to the marketing objective triggered by the target user. At this point, the marketing task candidate pool corresponding to the marketing objective is the same as the marketing task candidate pool corresponding to the marketing activity. Subsequently, the marketing platform can determine marketing tasks matching the target user's user characteristic data from the marketing task candidate pool corresponding to the marketing activity.

[0076] By setting different marketing task candidate pools based on different marketing objectives, and determining the marketing tasks that match the user from the marketing task candidate pool corresponding to the marketing objectives of the marketing activities triggered by the user, it is possible to filter out some marketing tasks based on marketing objectives before matching marketing tasks to users. Therefore, it is possible to improve marketing efficiency while realizing personalized marketing to users.

[0077] In some embodiments, each marketing task in the marketing task candidate pool can be labeled with its corresponding weight. For any given marketing task, its weight is associated with the historical task execution results corresponding to the target user. These historical task execution results may include the historical task completion rate.

[0078] In the above scenario, when the marketing platform determines a marketing task matching the target user's user characteristic data from the marketing task candidate pool, it can specifically determine the matching marketing task based on the target user's user characteristic data and the weights corresponding to each marketing task in the marketing task candidate pool. Furthermore, when determining a matching marketing task based on the user's user characteristic data and the weights of the marketing tasks, the marketing task that matches the user's user characteristic data and has a higher weight can be identified as the matching marketing task for that user.

[0079] In practical applications, for users, marketing tasks with a high completion rate in their past tasks can be assigned a higher weight, while marketing tasks with a 100% completion rate (i.e., marketing tasks that the user has already completed) can be assigned a lower weight. Similarly, marketing tasks that the user failed to complete or that were rejected by the user can be assigned a lower weight.

[0080] Specifically, the weight of marketing tasks that users have already completed, marketing tasks that users have failed to complete, and marketing tasks that users have rejected can be reduced based on penalty factors. Assuming the penalty factor for a marketing task that a user has already completed is α, the penalty factor for a marketing task that a user failed to complete is β, and the penalty factor for a marketing task that a user rejected is γ, then we have: 0 < γ < β < α < 1.

[0081] It should be noted that for marketing tasks rejected by users, the marketing task can be removed from the marketing task candidate pool for at least one marketing cycle; that is, the marketing task can be removed directly from the marketing task candidate pool when assigning marketing tasks to the user for at least one marketing cycle.

[0082] By assigning weights to marketing tasks that are linked to the user's historical task execution results for that task, and by determining the marketing tasks that match the user based on the user's user characteristic data and the weights of the marketing tasks, personalized marketing can be further realized, thereby improving marketing effectiveness.

[0083] The following is combined with, for example Figure 5 and Figure 6 The diagram illustrates the process of determining marketing tasks, and provides a detailed explanation of how to determine the marketing tasks that match a user based on the user's user characteristic data and the weight of the marketing tasks.

[0084] like Figure 5 As shown, in some embodiments, when the marketing platform determines a marketing task matching the user feature data from the marketing task candidate pool based on the user feature data of the target user and the weights corresponding to each marketing task in the marketing task candidate pool, it can specifically first input the full data contained in the user feature data of the target user into a trained machine learning model (which can be called the first machine learning model).

[0085] In practical applications, the aforementioned first machine learning model can be a machine learning model trained based on full data samples of user feature data corresponding to each marketing task in the aforementioned marketing task candidate pool. In this case, the first machine learning model can predict the matching degree (which can be referred to as the first matching degree) between the full data contained in the user feature data of the aforementioned target user and each marketing task in the marketing task candidate pool.

[0086] Subsequently, the aforementioned marketing platform can first determine the preset number of marketing tasks (e.g., the top 20) with the highest first matching degree (which can be called candidate marketing tasks), and then, based on the weight corresponding to each candidate marketing task, perform weighted processing on the first matching degree corresponding to each candidate marketing task, and based on the weighted first matching degree, determine the marketing tasks that match the user characteristic data of the aforementioned target users from these candidate marketing tasks.

[0087] For example, suppose the marketing platform identified two candidate marketing tasks, namely candidate marketing task 1 and candidate marketing task 2. Further suppose that the weight corresponding to candidate marketing task 1 is α and the first matching degree is x1, and the weight corresponding to candidate marketing task 2 is β and the first matching degree is y1. Then the weighted first matching degree corresponding to candidate marketing task 1 is α×x1, and the weighted first matching degree corresponding to candidate marketing task 2 is β×y1.

[0088] like Figure 6 As shown, in some embodiments, after determining the above-mentioned candidate marketing tasks, the marketing platform can further input the local data contained in the user feature data of the target user into the trained machine learning model (which may be referred to as the second machine learning model).

[0089] In practical applications, the aforementioned second machine learning model can be a machine learning model trained based on local data samples of user feature data corresponding to each marketing task in the aforementioned marketing task candidate pool. In this case, the second machine learning model can predict the matching degree (which can be referred to as the second matching degree) between the local data contained in the user feature data of the target user and each candidate marketing task.

[0090] Subsequently, when the marketing platform determines the marketing task that matches the user characteristic data of the target user from the candidate marketing tasks, it can first calculate the weighted sum of the first matching degree and the second matching degree corresponding to each candidate marketing task, and then further weight the weighted sum corresponding to each candidate marketing task based on the weight corresponding to each candidate marketing task. Based on the weighted sum, the marketing task that matches the user characteristic data can be determined from these candidate marketing tasks.

[0091] Continuing with the example above, let's assume that the weights set for the first matching degree and the second matching degree are m and n, respectively. Further, let's assume that the second matching degree corresponding to candidate marketing task 1 is x2 and the second matching degree corresponding to candidate marketing task 2 is y2. Then, the weighted sum corresponding to candidate marketing task 1 is α×(m×x1+n×x2) and the weighted sum corresponding to candidate marketing task 2 is β×(m×y1+n×y2).

[0092] In practical applications, both the first and second machine learning models described above can be based on GBDT (Gradient Boosting Decision Tree), allowing for iterative training using the decision tree to obtain the optimal solution. When training these two models, LightGBM (Light Gradient Boosting Machine) can be used as the training tool; LightGBM features fast training speed and low memory consumption.

[0093] In some embodiments, the aforementioned user characteristic data may include: the user's historical behavior data (e.g., historical data related to the user's actual performance in fulfilling behavioral tasks in a marketing campaign); user profiles; and / or the user's stage in the user lifecycle (e.g., introductory stage, growth stage, maturity stage, dormant stage, churn stage, etc.).

[0094] Specifically, the aforementioned user characteristic data may include: historical task behavior; historical task characteristics; historical reward characteristics; user marketing characteristics; and / or, basic user profile. The breakdown of these five types of user characteristic data is shown in Table 1 below:

[0095] Historical task behavior Number of orders Sharing preferences Duration of stay Annual spending Historical mission characteristics Task participation Task completion rate Type preference Difficulty Preference Historical reward characteristics Prize usage rate Historical prize value Prize collection rate Expired prizes User Marketing Characteristics New and old customers User maturity User Value User Level User Basic Profile gender Age group Profession hobbies

[0096] Table 1

[0097] It should be noted that the user feature data includes all types of user feature data. The complete data sample of user feature data is the sample of all types of user feature data.

[0098] Accordingly, in some embodiments, the partial data included in the user characteristic data of the target user may include: user characteristic data related to the marketing tasks recently performed by the target user from the full data included in the user characteristic data of the target user. The partial data sample of user characteristic data corresponding to the marketing task may include: a data sample of user characteristic data related to the marketing task itself from the full data sample of user characteristic data corresponding to the marketing task. For example, partial data may include: historical task behavior; historical task characteristics; and / or, historical reward characteristics.

[0099] By using a full-parameter model trained on full data samples of user feature data corresponding to marketing tasks to predict the matching degree between user feature data and marketing tasks, a second prediction is made using a local-parameter model trained on partial data samples of user feature data corresponding to marketing tasks. Based on the weighted sum of the two predictions, the final marketing task matching the user's user feature data is determined. Since the partial data samples of user feature data focus on user feature data related to marketing tasks that have recently performed marketing tasks, attention can be paid to the user data that has been recently fed back, thereby further improving the accuracy of marketing task matching.

[0100] Step 203: Assign the marketing task to the target user so that the target user can perform the behavioral fulfillment task, and after the target user has completed the behavioral fulfillment task, issue the behavioral fulfillment reward to the target user so that the target user can claim the behavioral fulfillment reward.

[0101] In this embodiment, when the marketing platform determines a marketing task that matches the user characteristic data of the target user, it can assign the marketing task to the target user, thereby enabling the target user to perform the behavioral fulfillment task in the marketing task.

[0102] Subsequently, once the target user completes the behavioral fulfillment task, the marketing platform can issue the behavioral fulfillment reward for the marketing task to the target user, allowing the target user to claim the behavioral fulfillment reward.

[0103] Specifically, the marketing platform can assign the aforementioned behavioral fulfillment task to the target user through a client corresponding to that target user, allowing the target user to execute the task on that client. The client can monitor the target user's progress on the task in real time, and upon detecting that the target user has completed the task, send a notification message to the marketing platform instructing the target user to complete the task. Upon receiving this notification message, the marketing platform can determine whether the target user has completed the task. Alternatively, the client can monitor the target user's progress on the task in real time and send this progress information to the marketing platform, allowing the marketing platform to determine whether the target user has completed the task based on the progress data.

[0104] Subsequently, once the target user has completed the aforementioned performance commitment task, the marketing platform can issue the performance commitment reward to the target user through the aforementioned client, allowing the target user to receive and use the performance commitment reward on the client.

[0105] In some embodiments, the aforementioned behavioral performance task may include: the correspondence between standardized behaviors and performance restriction rules.

[0106] The aforementioned standardized behavior can be achieved by standardizing data representing user behavior based on a preset standardized behavior format, resulting in data with that format. This standardized behavior format can be set by technical personnel according to actual needs; for example, it can include the six elements shown in Table 2 below: who, where, when, do, what, and how.

[0107] Zhang San APP homepage First visit Browse You May Like Module 10 seconds Li Si Limited-time purchase page During the big promotion Place an order X types of cat food 50 yuan

[0108] Table 2

[0109] Based on the standardized behavior format shown in Table 2 above, the user behavior of "Zhang San visits the APP for the first time and browses the 'You May Like' module on the APP homepage for 10 seconds" can be transformed into the standardized behavior of "Zhang San, APP homepage, first visit, browse, 'You May Like' module, 10 seconds"; the user behavior of "Li Si orders X cat food products through the limited-time purchase page during the promotion and pays 50 yuan" can be transformed into the standardized behavior of "Li Si, limited-time purchase page, promotion period, order, X cat food products, 50 yuan".

[0110] In practical applications, the aforementioned standardized behaviors can include standardized viral marketing assistance, sharing to invite new users, user check-in, clicking within the app or webpage, browsing within the app or webpage, placing an order in a specific scenario, adding items to the shopping cart, creating a user profile, receiving a red envelope in a specific part of the app, opening app notifications, and obtaining virtual goods.

[0111] The aforementioned performance restriction rules can be used to restrict standardized behaviors in fulfilling performance; that is, the performance restriction rules can be rules used to restrict the specific content and frequency of standardized behaviors.

[0112] In practical applications, the aforementioned performance restriction rules may include the number of orders, the quantity of goods purchased, the minimum order amount, the number of days of check-in, the order interval, the browsing time, and the richness of the profile content.

[0113] In the above circumstances, the marketing platform can determine whether the target user has completed the above-mentioned behavioral fulfillment task by the following methods: based on the above-mentioned standardized behavior format, the user behavior of the target user is transformed into standardized behavior; based on the correspondence between the standardized behavior in the behavioral fulfillment task and the fulfillment restriction rules, it is determined whether the transformed standardized behavior complies with its corresponding fulfillment restriction rules; if the transformed standardized behavior complies with its corresponding fulfillment restriction rules, it is determined that the target user has completed the behavioral fulfillment task.

[0114] By transforming user behavior into standardized behavior and determining whether the transformed standardized behavior conforms to its corresponding performance constraint rules, it is possible to determine whether the user has completed the performance constraint task. This ensures that the determination of whether the user has completed the performance constraint task is based on the same standard, avoiding the problems of low efficiency and poor accuracy in determining whether the user has completed the performance constraint task due to the complex and inconsistent data formats of user behavior and performance constraint rules.

[0115] In some embodiments, for any of the above-described behavioral performance tasks, the behavioral performance task may include multiple subtasks. These multiple subtasks may have specific relationships, which may include one or more of the following: parent-child integration relationship, mutual exclusion relationship, symbiotic relationship, serial relationship, and parallel relationship.

[0116] In the above circumstances, the user will be deemed to have completed the performance of the performance task only after the user has completed all the sub-tasks that should be performed in the performance task.

[0117] For example, suppose the aforementioned behavior fulfillment task includes two subtasks, subtask A and subtask B, and these two subtasks are mutually exclusive. Then, once the target user completes either subtask A or subtask B, it can be determined that the target user has completed the behavior fulfillment task. Alternatively, suppose the aforementioned behavior fulfillment task includes three subtasks, subtask X, subtask Y, and subtask Z, and these three subtasks are sequentially related. Then, once the target user completes subtask X, then subtask Y, and finally subtask Z, it can be determined that the target user has completed the behavior fulfillment task.

[0118] For any of the aforementioned performance-based rewards, the performance-based reward may include: physical resource rewards; and / or, virtual resource rewards. Physical resource rewards may include red envelopes, gift cards, coupons, points, physical goods, etc., while virtual resource rewards may include virtual assets such as badges, levels, tree-planting water droplets, pet community fish treats, game steps, and Wish World expansion licenses.

[0119] In addition, the method for obtaining the aforementioned performance rewards can be set. This method may include the amount to be obtained, the probability of obtaining the reward, the timing of obtaining the reward, whether manual collection is required, and the time limit for collection.

[0120] Step 204: Update the user characteristic data of the target user based on the task execution results and reward claim results corresponding to the target user.

[0121] In this embodiment, after assigning the marketing task to the target user, the marketing platform can further obtain the task execution result and reward claim result corresponding to the target user, as feedback on the target user's participation in the marketing activity.

[0122] The task execution results can indicate whether the user has completed the behavioral fulfillment tasks within the marketing task, the user's progress in fulfilling these tasks, and the success and failure rates. In other words, the task execution results are data related to the user's actual performance in fulfilling the behavioral fulfillment tasks within the marketing task. Similarly, the reward redemption results can indicate whether the user has received all or part of the behavioral fulfillment rewards within the marketing task, and whether the user has used all or part of the behavioral fulfillment rewards. In other words, the reward redemption results are data related to the user's actual receipt and use of the behavioral fulfillment rewards within the marketing task.

[0123] In practical applications, the client corresponding to the aforementioned target user can communicate with the aforementioned marketing platform, enabling the target user to perform the aforementioned behavioral fulfillment tasks and claim the aforementioned behavioral fulfillment rewards. Therefore, the task execution results and reward claim results corresponding to the target user can be directly stored in the marketing platform. In this case, the marketing platform can independently retrieve the task execution results and reward claim results corresponding to the target user.

[0124] Alternatively, the client corresponding to the aforementioned target user can proactively send the task execution results and reward claim results corresponding to that target user to the marketing platform.

[0125] Once the marketing platform obtains the task execution results and reward redemption results corresponding to the target user, it can update the user characteristic data of the target user based on the task execution results and reward redemption results.

[0126] In this scenario, the aforementioned marketing platform can then assign marketing tasks to the target user that match the target user's updated user characteristic data.

[0127] In some embodiments, the marketing platform can also, for each marketing task in the marketing task candidate pool, statistically analyze the task execution results and reward claiming results corresponding to each marketing task, and based on these results, identify inefficient marketing tasks. Subsequently, the marketing platform can output an alarm notification corresponding to the identified inefficient marketing task to the operator associated with the marketing activity.

[0128] In practical applications, the aforementioned inefficient marketing tasks may include one or more of the following: marketing tasks with a return on investment (ROI) less than a preset first threshold; marketing tasks with user engagement less than a preset second threshold; and marketing tasks with task completion less than a preset third threshold. Therefore, these inefficient marketing tasks are those where users have a low willingness to perform them; because users have a low willingness to perform these inefficient marketing tasks, the marketing effect of assigning these inefficient marketing tasks to users is poor.

[0129] By identifying inefficient marketing tasks from the marketing task candidate pool and sending alerts to the operators corresponding to these inefficient marketing tasks, operators can be aware of these inefficient marketing tasks and be prompted to adjust or remove them, thereby ensuring the quality of online marketing tasks.

[0130] In the above technical solution, the marketing platform can respond to the user's triggered operation for the marketing activity, obtain the user's user characteristic data, and determine the marketing task that matches the user's user characteristic data from the marketing candidate pool corresponding to the marketing platform. Then, the marketing task can be assigned to the user, so that the user can perform the behavioral fulfillment task in the marketing task. After the user completes the behavioral fulfillment task, the user is issued the behavioral fulfillment reward of the marketing task, so that the user can claim the behavioral fulfillment reward. Finally, the user's user characteristic data can be updated based on the task execution result and reward claim result corresponding to the user.

[0131] The above approach offers several advantages. First, it transforms marketing campaigns into marketing tasks. When a user triggers a campaign, a matching task can be assigned from a pool of potential users, rather than directly delivering the campaign. Therefore, when marketing strategies change, only the assigned task needs to be modified, or the task itself only slightly altered, reducing costs and improving timeliness. Second, based on user characteristic data, marketing tasks matching the user's data are assigned, enabling personalized marketing. Third, after a user completes a marketing task and claims its reward, their user characteristic data is updated. This allows for subsequent matching tasks based on the updated data, introducing user data feedback and improving marketing effectiveness.

[0132] Exemplary media

[0133] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 7 A marketing medium based on an exemplary embodiment of the present invention will be described.

[0134] In this exemplary embodiment, the above method can be implemented by a program product, such as a portable compact disc read-only memory (CD-ROM) containing program code, which can run on a device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0135] This program product can be produced using any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium.

[0136] A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0137] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0138] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RE, etc., or any suitable combination thereof.

[0139] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0140] Exemplary device

[0141] After introducing the medium of exemplary embodiments of the present invention, the following references are made. Figure 8 An apparatus for marketing, according to an exemplary embodiment of the present invention, will be described.

[0142] The implementation process of the functions and roles of each module in the following apparatus is detailed in the corresponding steps of the above method, and will not be repeated here. The apparatus embodiments are basically corresponding to the method embodiments; therefore, relevant details can be found in the descriptions of the method embodiments.

[0143] refer to Figure 8 , Figure 8 A marketing device according to an embodiment of the present invention is illustrated schematically.

[0144] The aforementioned marketing device can be applied to a marketing platform; the device includes:

[0145] The acquisition module 801 is used to acquire user characteristic data of the target user in response to the target user's triggered operation for the marketing activity;

[0146] The first determining module 802 is used to determine, based on the user characteristic data of the target user, a marketing task matching the user characteristic data from a marketing task candidate pool corresponding to the marketing platform; wherein, the marketing task includes a behavior fulfillment task and a behavior fulfillment reward;

[0147] The allocation module 803 is used to allocate the marketing task to the target user so that the target user can perform the behavior fulfillment task, and after the target user has completed the behavior fulfillment task, to issue the behavior fulfillment reward to the target user so that the target user can claim the behavior fulfillment reward;

[0148] The update module 804 is used to update the user characteristic data of the target user based on the task execution results and reward claim results corresponding to the target user.

[0149] Optionally, the behavioral performance task includes a correspondence between standardized behaviors and performance restriction rules; wherein, the performance restriction rules are used to restrict the standardized behaviors required to complete the performance.

[0150] The following methods are used to determine whether the target user has completed the behavioral fulfillment task:

[0151] Based on a preset standardized behavior format, the user behavior of the target user is transformed into standardized behavior;

[0152] Based on the correspondence in the behavioral performance task, determine whether the transformed standardized behavior conforms to the corresponding performance restriction rules;

[0153] If so, confirm that the target user has completed the behavioral fulfillment task.

[0154] Optionally, the behavior fulfillment task includes multiple sub-tasks; wherein the relationship between the multiple sub-tasks includes one or more of the following: parent-child integration relationship, mutual exclusion relationship, symbiotic relationship, serial relationship, and parallel relationship;

[0155] The performance reward includes: physical resource rewards; and / or, virtual resource rewards.

[0156] Optionally, the target user's triggering operation for the marketing campaign includes: the target user's triggering operation for interactive controls in the user-facing page related to the marketing campaign.

[0157] Optionally, the device further includes:

[0158] The second determining module 805 is used to determine inefficient marketing tasks based on the task execution results and reward claim results corresponding to each marketing task in the marketing task candidate pool; wherein, the inefficient marketing tasks include one or more of the following: marketing tasks with an input-output ratio less than a preset first threshold; marketing tasks with user participation less than a preset second threshold; and marketing tasks with task completion less than a preset third threshold.

[0159] Alarm module 806 is used to output alarm notifications to the operator corresponding to the marketing activity and the inefficient marketing task.

[0160] Optionally, the marketing platform corresponds to multiple marketing task candidate pools; different marketing task candidate pools in the multiple marketing task candidate pools correspond to different marketing objectives;

[0161] The first determining module 802 is specifically used for:

[0162] Based on the marketing objectives corresponding to the marketing campaign, a marketing task candidate pool corresponding to the marketing campaign is determined from multiple marketing task candidate pools corresponding to the marketing platform;

[0163] Based on the user characteristic data of the target user, marketing tasks that match the user characteristic data are determined from the marketing task candidate pool corresponding to the marketing campaign.

[0164] Optionally, each marketing task in the marketing task candidate pool is labeled with its corresponding weight; the weight is associated with the historical task execution results corresponding to the target user; the historical task execution results include the historical task completion rate;

[0165] The first determining module 802 is specifically used for:

[0166] Based on the user characteristic data of the target user and the weights corresponding to each marketing task in the marketing task candidate pool, marketing tasks that match the user characteristic data are determined from the marketing task candidate pool.

[0167] Optionally, the first determining module 802 is specifically used for:

[0168] The first machine learning model is trained by inputting the full data of the user feature data of the target user into the first machine learning model, so that the first machine learning model predicts the first matching degree between the user feature data of the target user and each marketing task in the marketing task candidate pool; wherein, the first machine learning model is trained based on the full data samples of user feature data corresponding to each marketing task in the marketing task candidate pool.

[0169] Determine a preset number of candidate marketing tasks with the highest first matching degree;

[0170] Based on the weights corresponding to each candidate marketing task, the first matching degree corresponding to each candidate marketing task is weighted, and based on the weighted first matching degree, the marketing task that matches the user feature data is determined from the candidate marketing tasks.

[0171] Optionally, the first determining module 802 is further configured to:

[0172] The local data contained in the user feature data of the target user is input into the trained second machine learning model, so that the second machine learning model predicts the second matching degree between the user feature data of the target user and each candidate marketing task; wherein, the second machine learning model is trained based on local data samples of user feature data corresponding to each marketing task in the marketing task candidate pool;

[0173] Calculate the weighted sum of the first matching degree and the second matching degree corresponding to each candidate marketing task;

[0174] The first determining module 802 is specifically used for:

[0175] Based on the weights corresponding to each candidate marketing task, the weighted sum corresponding to each candidate marketing task is further weighted, and based on the weighted sum, the marketing task that matches the user feature data is determined from the candidate marketing tasks.

[0176] Optionally, the partial data included in the user characteristic data of the target user includes: user characteristic data related to the marketing tasks recently performed by the target user in the full data included in the user characteristic data of the target user;

[0177] A partial data sample of user feature data corresponding to the marketing task includes: a data sample of user feature data related to the marketing task from the full data sample of user feature data corresponding to the marketing task.

[0178] Optionally, the user characteristic data includes: historical task behavior; historical task characteristics; historical reward characteristics; user marketing characteristics; and / or, user basic profile.

[0179] Exemplary computing device

[0180] After introducing the methods, media, and apparatus of exemplary embodiments of the present invention, the following references are made. Figure 9 A computing device for marketing, according to an exemplary embodiment of the present invention, will be described.

[0181] Figure 9 The computing device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0182] like Figure 9 As shown, the computing device 900 is presented in the form of a general-purpose computing device. The components of the computing device 900 may include, but are not limited to: at least one processing unit 901, at least one storage unit 902, and a bus 903 connecting different system components (including the processing unit 901 and the storage unit 902).

[0183] The 903 bus includes a data bus, a control bus, and an address bus.

[0184] Storage unit 902 may include readable media in the form of volatile memory, such as random access memory (RAM) 9021 and / or cache memory 9022, and may further include readable media in the form of non-volatile memory, such as read-only memory (ROM) 9023.

[0185] Storage unit 902 may also include a program / utility 9025 having a set (at least one) of program modules 9024, such program modules 9024 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0186] The computing device 900 can also communicate with one or more external devices 904 (such as a keyboard, pointing device, etc.).

[0187] This communication can be performed via input / output (I / O) interface 905. Furthermore, the computing device 900 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 906. Figure 9As shown, network adapter 906 communicates with other modules of computing device 900 via bus 903. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with computing device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0188] It should be noted that although several units / modules or sub-units / modules of the marketing device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0189] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0190] While the spirit and principles of the invention have been described with reference to several specific embodiments, it should be understood that the invention is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for ease of description. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A marketing method applied to a marketing platform; each marketing task in a marketing task candidate pool corresponding to the marketing platform is labeled with its corresponding weight; The weights are associated with the historical task execution results of the target user. The historical task execution result includes the historical task completion degree; the method includes: In response to a target user's triggered action in relation to a marketing campaign, the user characteristic data of the target user is obtained; The first machine learning model is trained by inputting the full data of the user feature data of the target user into the first machine learning model, so that the first machine learning model predicts the first matching degree between the user feature data of the target user and each marketing task in the marketing task candidate pool; wherein, the first machine learning model is trained based on the full data samples of user feature data corresponding to each marketing task in the marketing task candidate pool. The local data contained in the user feature data of the target user is input into the trained second machine learning model, so that the second machine learning model predicts the second matching degree between the user feature data of the target user and each candidate marketing task; wherein, the second machine learning model is trained based on local data samples of user feature data corresponding to each marketing task in the marketing task candidate pool; Determine a preset number of candidate marketing tasks with the highest first matching degree, and calculate the weighted sum of the first matching degree and the second matching degree corresponding to each candidate marketing task; Based on the weights corresponding to each candidate marketing task, the weighted sum corresponding to each candidate marketing task is further weighted, and based on the weighted sum, the marketing task matching the user feature data is determined from the candidate marketing tasks; wherein, the marketing task includes behavioral fulfillment task and behavioral fulfillment reward. The marketing task is assigned to the target user so that the target user performs the behavioral fulfillment task, and after the target user completes the behavioral fulfillment task, the behavioral fulfillment reward is issued to the target user so that the target user can claim the behavioral fulfillment reward; Based on the task execution results and reward redemption results corresponding to the target user, update the user characteristic data of the target user.

2. The method according to claim 1, wherein the behavioral performance task includes the correspondence between standardized behaviors and performance restriction rules; wherein, The performance restriction rules are used to restrict standardized behaviors for fulfilling performance; The following methods are used to determine whether the target user has completed the behavioral fulfillment task: Based on a preset standardized behavior format, the user behavior of the target user is transformed into standardized behavior; Based on the correspondence in the behavioral performance task, determine whether the transformed standardized behavior conforms to the corresponding performance restriction rules; If so, confirm that the target user has completed the behavioral fulfillment task.

3. The method according to claim 1, wherein the behavioral performance task includes multiple sub-tasks; wherein, The relationships between the multiple subtasks include one or more of the following: parent-child integration relationship, mutual exclusion relationship, symbiotic relationship, serial relationship, and parallel relationship; The performance reward includes: physical resource reward; And / or, virtual resource rewards.

4. The method according to claim 1, wherein the target user's triggered action in response to the marketing campaign includes: The target user's actions are triggered by interactive controls on user-facing pages related to the marketing campaign.

5. The method according to claim 1, further comprising: Based on the task execution results and reward claim results corresponding to each marketing task in the marketing task candidate pool, inefficient marketing tasks are identified; wherein, the inefficient marketing tasks include one or more of the following: marketing tasks with an input-output ratio less than a preset first threshold; marketing tasks with user participation less than a preset second threshold; and marketing tasks with task completion less than a preset third threshold. Output alarm notifications corresponding to the inefficient marketing tasks to the operators associated with the marketing campaign.

6. The method according to claim 1, wherein the marketing platform corresponds to multiple marketing task candidate pools; different marketing task candidate pools in the multiple marketing task candidate pools correspond to different marketing objectives; The step of determining marketing tasks matching the user characteristic data from the marketing task candidate pool corresponding to the marketing platform based on the user characteristic data of the target user includes: Based on the marketing objectives corresponding to the marketing campaign, a marketing task candidate pool corresponding to the marketing campaign is determined from multiple marketing task candidate pools corresponding to the marketing platform; Based on the user characteristic data of the target user, marketing tasks that match the user characteristic data are determined from the marketing task candidate pool corresponding to the marketing campaign.

7. The method according to claim 1, wherein the user characteristic data of the target user includes local data, comprising: The user characteristic data of the target user includes user characteristic data related to the marketing tasks recently performed by the target user from the full data; A partial data sample of user feature data corresponding to the marketing task includes: a data sample of user feature data related to the marketing task from the full data sample of user feature data corresponding to the marketing task.

8. The method according to claim 1, wherein the user feature data comprises: Historical task behavior; historical task characteristics; historical reward characteristics; user marketing characteristics; And / or, basic user profile.

9. A marketing device applied to a marketing platform; each marketing task in a marketing task candidate pool corresponding to the marketing platform is labeled with its corresponding weight; The weights are associated with the historical task execution results of the target user. The historical task execution result includes the historical task completion degree; the device includes: The acquisition module is used to acquire user characteristic data of the target user in response to the target user's triggered operation for the marketing campaign; A first determining module is configured to input the full data contained in the user feature data of the target user into a first machine learning model that has been trained, so that the first machine learning model predicts a first matching degree between the user feature data of the target user and each marketing task in the marketing task candidate pool; wherein, the first machine learning model is trained based on full data samples of user feature data corresponding to each marketing task in the marketing task candidate pool; input the partial data contained in the user feature data of the target user into a second machine learning model that has been trained, so that the second machine learning model predicts a second matching degree between the user feature data of the target user and each candidate marketing task; wherein, the second machine learning model is trained based on partial data samples of user feature data corresponding to each marketing task in the marketing task candidate pool; determine a preset number of candidate marketing tasks with the highest first matching degree, and calculate a weighted sum of the first matching degree and the second matching degree corresponding to each candidate marketing task; further weight the weighted sum corresponding to each candidate marketing task based on the weights corresponding to each candidate marketing task, and determine the marketing task matching the user feature data from the candidate marketing tasks based on the weighted sum; wherein, the marketing task includes a behavior fulfillment task and a behavior fulfillment reward; The allocation module is used to allocate the marketing task to the target user so that the target user can perform the behavioral fulfillment task, and after the target user has completed the behavioral fulfillment task, to issue the behavioral fulfillment reward to the target user so that the target user can claim the behavioral fulfillment reward; The update module is used to update the user characteristic data of the target user based on the task execution results and reward claim results corresponding to the target user.

10. The apparatus according to claim 9, wherein the behavioral performance task includes a correspondence between standardized behaviors and performance restriction rules; wherein, The performance restriction rules are used to restrict standardized behaviors for fulfilling performance; The following methods are used to determine whether the target user has completed the behavioral fulfillment task: Based on a preset standardized behavior format, the user behavior of the target user is transformed into standardized behavior; Based on the correspondence in the behavioral performance task, determine whether the transformed standardized behavior conforms to the corresponding performance restriction rules; If so, confirm that the target user has completed the behavioral fulfillment task.

11. The apparatus according to claim 9, wherein the behavioral performance task comprises multiple sub-tasks; wherein, The relationships between the multiple subtasks include one or more of the following: parent-child integration relationship, mutual exclusion relationship, symbiotic relationship, serial relationship, and parallel relationship; The performance reward includes: physical resource reward; And / or, virtual resource rewards.

12. The apparatus of claim 9, wherein the target user's triggering operation for the marketing activity includes: The target user's actions are triggered by interactive controls on user-facing pages related to the marketing campaign.

13. The apparatus of claim 9, further comprising: The second determining module is used to determine inefficient marketing tasks based on the task execution results and reward claiming results corresponding to each marketing task in the marketing task candidate pool; wherein, the inefficient marketing tasks include one or more of the following: marketing tasks with an input-output ratio less than a preset first threshold; marketing tasks with user participation less than a preset second threshold; and marketing tasks with task completion less than a preset third threshold. The alarm module is used to output alarm notifications to the operators corresponding to the marketing activities and to the inefficient marketing tasks.

14. The apparatus according to claim 9, wherein the marketing platform corresponds to a plurality of marketing task candidate pools; different marketing task candidate pools in the plurality of marketing task candidate pools correspond to different marketing objectives; The first determining module is specifically used for: Based on the marketing objectives corresponding to the marketing campaign, a marketing task candidate pool corresponding to the marketing campaign is determined from multiple marketing task candidate pools corresponding to the marketing platform; Based on the user characteristic data of the target user, marketing tasks that match the user characteristic data are determined from the marketing task candidate pool corresponding to the marketing campaign.

15. The apparatus according to claim 9, wherein the user characteristic data of the target user includes partial data, comprising: The user characteristic data of the target user includes user characteristic data related to the marketing tasks recently performed by the target user from the full data; A partial data sample of user feature data corresponding to the marketing task includes: a data sample of user feature data related to the marketing task from the full data sample of user feature data corresponding to the marketing task.

16. The apparatus according to claim 9, wherein the user characteristic data comprises: Historical task behavior; historical task characteristics; historical reward characteristics; user marketing characteristics; And / or, basic user profile.

17. A medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of claims 1 to 8.

18. A computing device, comprising: processor; Memory used to store processor-executable programs; The processor implements the method as described in any one of claims 1 to 8 by running the executable program.

Images