Task distribution method, device, electronic device and storage medium

Abstract

The present disclosure relates to a task issuing method, device, electronic device, and storage medium, and relates to the field of computer technology. The method includes: clustering multiple user accounts based on historical task data and corresponding historical task resource data of multiple user accounts to obtain at least one user account group; determining the target task increase of each user account group based on the historical task data and corresponding historical task resource data of the user accounts in each user account group; for each user account, determining the target task data of the user account based on the historical task data of the user account and the target task increase of the user account group to which it belongs; and issuing the target task to the user account according to the target task data of the user account. In this way, appropriate tasks can be issued to each user account, achieving personalized task issuance to user accounts and improving the matching degree between user accounts and tasks.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a task issuing method, device, electronic device, and storage medium. Background Art

[0002] Currently, various Internet products or social platforms usually assign tasks to users. When users complete the tasks, the Internet products or social platforms will provide users with task resources.

[0003] In related technologies, when assigning tasks to users, the quantile method is usually used. Based on the historical completion status of multiple users on the task, a unified task is set for multiple users based on experience. This method of task assignment is prone to the situation where the tasks assigned to users do not match the users. Summary of the Invention

[0004] The present disclosure provides a task issuing method, device, electronic device and storage medium to at least solve the problem in the related art that the task issuing method is prone to mismatch between the task issued to the user and the user.

[0005] The technical solutions disclosed in this disclosure are as follows:

[0006] According to a first aspect of an embodiment of the present disclosure, a task issuing method is provided, comprising: clustering a plurality of user accounts based on their historical task data and corresponding historical task resource data to obtain at least one user account group; determining a target task increase for each user account group based on their historical task data and corresponding historical task resource data; determining, for each user account, target task data for the user account based on its historical task data and the target task increase for the user account group to which it belongs; and issuing a target task to the user account according to its target task data.

[0007] As a first possible scenario of an embodiment of the present disclosure, determining a target task increase for each user account group based on historical task data and corresponding historical task resource data of user accounts in each user account group includes: inputting the historical task data and corresponding historical task resource data of the user accounts in each user account group into a task model to obtain an output value of the task model; wherein the task model uses the task increase and task-resource ratio of each user account group as model parameters, the task model determines the task participation of each user account group based on the historical task data, corresponding historical task resource data, task increase and task-resource ratio of each user account group, and outputs the output value based on the task participation of each user account group and the task-resource ratio of each user account group; adjusting the task increase within a first preset range and adjusting the task-resource ratio within a second preset range so that the output value of the task model reaches a maximum value; determining the task increase when the output value of the task model reaches the maximum value as the target task increase, and determining the task-resource ratio when the output value of the task model reaches the maximum value as the target task resource ratio.

[0008] As a second possible situation of an embodiment of the present disclosure, the way in which the task model outputs the output value includes: for each group of task increases and task resource ratios, determining the task participation of each user account in each of the user account groups based on the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, and the task increases and the task resource ratios in the group; determining the task participation of each of the user account groups based on the task participation of each user account in each of the user account groups; and outputting the output value of the task model based on the task participation of each of the user account groups and the task resource ratios of each of the user account groups.

[0009] As a third possible scenario of the embodiment of the present disclosure, for each group of task increase and task resource ratio, the task participation of each user account in each of the user account groups is determined according to the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, and the task increase and the task resource ratio in the group, including: for each of the user accounts in each of the user account groups, the task increase of the user account according to the historical task data of the user account, the task increase of the user account group to which the user account belongs, and the historical task data of each user account in the user account group; according to the historical task data of the user account and the historical task data of the user account Based on the task increment of the user account, determine the task increment corresponding to the task increment of the user account; determine the task resource data corresponding to the task increment of the user account according to the task increment corresponding to the task increment of the user account and the task resource ratio of the user account group to which the user account belongs; obtain the task execution degree of the user account for the task increment according to the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account; obtain the task completion degree of the user account for the task increment according to the historical task data of the user account; determine the task participation degree of the user account according to the task execution degree and the task completion degree.

[0010] As a fourth possible scenario of an embodiment of the present disclosure, obtaining the task completion degree of the user account for the task increment based on the historical task data of the user account includes: determining the normal distribution to which the historical task data of the user account belongs based on the historical task data of the user account; and determining the task completion degree of the user account for the task increment based on the mean and variance of the normal distribution.

[0011] As a fifth possible situation of an embodiment of the present disclosure, the task execution degree of the user account for the task increment is obtained based on the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account, including: when the ratio of the task resource data to the historical task resource data is greater than a preset value, determining the task execution degree to be a first value; when the ratio of the task resource data to the historical task resource data is less than or equal to a preset value, determining the task execution degree to be a second value.

[0012] As a sixth possible situation of an embodiment of the present disclosure, the task execution degree of the user account for the task increment is a first value or a second value; determining the task participation degree of the user account based on the task execution degree and the task completion degree includes: when the task execution degree of the user account for the task increment is a first value, determining the task completion degree of the user account for the task increment as the task participation degree of the user account; when the task execution degree of the user account for the task increment is a second value, determining the task participation degree of the user account to be 0.

[0013] As the seventh possible situation of the embodiment of the present disclosure, the target task data of each user account is determined according to the historical task data of the user account and the target task increase rate of the user account group to which it belongs, including: for each user account, the target task increase rate of the user account is determined according to the historical task data of the user account, the target task increase rate of the user account group to which it belongs, and the historical task data of each user account in the user account group to which it belongs; the target task data of the user account is determined according to the historical task data of the user account and the target task increase rate of the user account.

[0014] As the eighth possible situation of the embodiment of the present disclosure, the method also includes: determining the target task resource data of the user account based on the historical task data of the user account, the target task increase rate of the user account, and the target task resource ratio of the user account; when it is determined that the client logged into the user account has completed the target task data, issuing corresponding target task resources to the client according to the target task resource data of the user account.

[0015] According to a second aspect of an embodiment of the present disclosure, a task issuing device is provided, comprising: a clustering module, configured to cluster a plurality of user accounts according to their historical task data and corresponding historical task resource data, to obtain at least one user account group; a first determination module, configured to determine a target task increase for each user account group according to their historical task data and corresponding historical task resource data; a second determination module, configured to determine, for each user account, the target task data of the user account according to its historical task data and the target task increase of the user account group to which it belongs; and a first issuing module, configured to issue a target task to the user account according to its target task data.

[0016] As a first possible scenario of an embodiment of the present disclosure, the first determination module includes: an acquisition unit configured to input historical task data and corresponding historical task resource data of user accounts in each of the user account groups into a task model to obtain an output value of the task model; wherein the task model uses the task increase and task resource ratio of each of the user account groups as model parameters, the task model determines the task participation of each of the user account groups based on the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, the task increase and task resource ratio of each of the user account groups, and outputs the output value based on the task participation of each of the user account groups and the task resource ratio of each of the user account groups; an adjustment unit configured to adjust the task increase within the first preset range and the task resource ratio within the second preset range so that the output value of the task model reaches a maximum value; the first determination unit is configured to determine the task increase when the output value of the task model reaches the maximum value as the target task increase, and determine the task resource ratio when the output value of the task model reaches the maximum value as the target task resource ratio.

[0017] As a second possible situation of an embodiment of the present disclosure, the acquisition unit is specifically configured to perform: for each group of task increases and task resource ratios, determining the task participation of each user account in each of the user account groups based on the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, and the task increases and the task resource ratios in the group; determining the task participation of each of the user account groups based on the task participation of each user account in each of the user account groups; and outputting the output value of the task model based on the task participation of each of the user account groups and the task resource ratios of each of the user account groups.

[0018] As a third possible situation of an embodiment of the present disclosure, the acquisition unit is specifically configured to perform: for each user account in each user account group, determining the task increase of the user account based on the historical task data of the user account, the task increase of the user account group to which the user account belongs, and the historical task data of each user account in the user account group; determining the task increment corresponding to the task increase of the user account based on the historical task data of the user account and the task increase of the user account; determining the task resource data corresponding to the task increase of the user account based on the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs; acquiring the task execution degree of the user account for the task increase based on the task resource data corresponding to the task increase of the user account and the historical task resource data corresponding to the historical task data of the user account; acquiring the task completion degree of the user account for the task increase based on the historical task data of the user account; and determining the task participation degree of the user account based on the task execution degree and the task completion degree.

[0019] As a fourth possible situation of an embodiment of the present disclosure, the acquisition unit is specifically configured to perform: determining the normal distribution to which the historical task data of the user account belongs based on the historical task data of the user account; and determining the task completion degree of the user account for the task increment based on the mean and variance of the normal distribution.

[0020] As the fifth possible situation of the embodiment of the present disclosure, the acquisition unit is specifically configured to perform: when the ratio of the task resource data to the historical task resource data is greater than a preset value, determine the task execution degree as a first value; when the ratio of the task resource data to the historical task resource data is less than or equal to a preset value, determine the task execution degree as a second value.

[0021] As a sixth possible situation of an embodiment of the present disclosure, the task execution degree of the user account for the task increment is a first value or a second value; the acquisition unit is specifically configured to execute: when the task execution degree of the user account for the task increment is a first value, the task completion degree of the user account for the task increment is determined as the task participation degree of the user account; when the task execution degree of the user account for the task increment is a second value, the task participation degree of the user account is determined to be 0.

[0022] As the seventh possible situation of the embodiment of the present disclosure, the second determination module includes: a second determination unit, configured to determine the target task increase of the user account for each of the user accounts based on the historical task data of the user account, the target task increase of the user account group to which it belongs, and the historical task data of each user account in the user account group to which it belongs; a third determination unit, configured to determine the target task data of the user account based on the historical task data of the user account and the target task increase of the user account.

[0023] As the eighth possible situation of the embodiment of the present disclosure, the device further includes: a third determination module, configured to determine the target task resource data of the user account based on the historical task data of the user account, the target task increase rate of the user account, and the target task resource ratio of the user account; a second issuance module, configured to issue corresponding target task resources to the client according to the target task resource data of the user account when it is determined that the client logged into the user account has completed the target task data.

[0024] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the task dispatching method proposed in the embodiment of the first aspect of the present disclosure.

[0025] According to the fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of an electronic device, the electronic device can execute the task dispatching method proposed in the embodiment of the first aspect of the present disclosure.

[0026] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, which is executed by a processor to implement the task dispatching method proposed in the embodiment of the first aspect of the present disclosure.

[0027] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0028] By clustering multiple user accounts based on their historical task data and corresponding historical task resource data, at least one user account group is obtained. The target task increase of each user account group is determined based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data. For each user account, the target task data of the user account is determined based on the historical task data of the user account and the target task increase of the user account group to which it belongs. Then, the target task is issued to the user account according to the target task data of the user account. Appropriate tasks can be issued to each user account, thereby realizing personalized task issuance to user accounts and improving the matching degree between user accounts and tasks.

[0029] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0031] Figure 1 is a flowchart of a task issuing method according to an exemplary embodiment;

[0032] Figure 2 is a flowchart illustrating another method for issuing tasks according to an exemplary embodiment;

[0033] Figure 3 is a flowchart illustrating another method for issuing tasks according to an exemplary embodiment;

[0034] Figure 4 is a normal distribution graph showing historical task data of a user account according to an exemplary embodiment;

[0035] Figure 5 is a flowchart illustrating another method for issuing tasks according to an exemplary embodiment;

[0036] Figure 6 is a block diagram of a task issuing device according to an exemplary embodiment;

[0037] Figure 7 The figure is a block diagram of an electronic device for issuing tasks according to an exemplary embodiment. DETAILED DESCRIPTION

[0038] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0039] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0040] In related technologies, when assigning tasks to users, the quantile method is usually used. Based on the historical completion status of multiple users on the task, a unified task is set for multiple users based on experience. This method of task assignment is prone to the situation where the tasks assigned to users do not match the users.

[0041] For example, consider the task of liking works posted on social platforms. Assume that the number of likes received by a user account for a work posted is the task to be assigned. Related technologies typically use a quantile method based on the historical like counts of works posted by multiple user accounts over a period of time. For example, a 60th percentile historical like count is selected and used as the task value for the multiple user accounts. The task is then assigned to the user accounts based on the determined task value.

[0042] The task value determined by the above method is set based on experience and is not accurate for many user accounts. For example, when the historical like counts of works by multiple user accounts are very discrete, if a 60th percentile historical like count is selected as the task value, then for user accounts with low historical like counts, since the historical like counts of the user accounts are far lower than the task value, it is difficult for the user accounts to complete the task, and the possibility of the user accounts participating in the task will be very small. Therefore, the task value determined using the above method is not suitable for user accounts with low historical like counts of works.

[0043] In order to solve the above technical problems, the present disclosure proposes a task issuing method. The task issuing method of the embodiment of the present disclosure first clusters multiple user accounts based on their historical task data and corresponding historical task resource data to obtain at least one user account group, then determines the target task increase of each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data, and then determines the target task data of each user account based on the historical task data of the user account and the target task increase of the user account group to which it belongs, and then issues the target task to the user account according to the target task data of the user account. In this way, appropriate tasks can be issued to each user account, realizing personalized task issuance to user accounts and improving the matching degree between user accounts and tasks.

[0044] The task issuing method provided by the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0045] Figure 1 The figure is a flowchart of a method for issuing tasks according to an exemplary embodiment.

[0046] It should be noted that the executor of the task issuing method of the embodiment of the present disclosure may be a task issuing device, which may be an electronic device or may be configured in an electronic device to determine and issue tasks matching user accounts to multiple user accounts.

[0047] The electronic device can be any stationary or mobile computing device with a display screen that can install software products or run web products and perform data processing, such as mobile computing devices such as laptops, smartphones, and wearable devices, or stationary computing devices such as desktop computers, or other types of computing devices. The task issuing device can be an application installed on the electronic device or a software management tool for software products or web products, and the embodiments of the present disclosure are not limited thereto.

[0048] like Figure 1 As shown, the task issuing method may include the following steps 101-104.

[0049] In step 101 , multiple user accounts are clustered based on their historical task data and corresponding historical task resource data to obtain at least one user account group.

[0050] Among them, historical task data refers to the task data of the user account in the past period of time; historical task resource data refers to the task resource data obtained by the user account after completing tasks in the past period of time.

[0051] Taking the task of liking works published on social platforms as an example, historical task data may include the number of likes for works published by the user account on the social platform in the past period of time; historical task resource data may include the number of exposures of works published by the user account on the social platform in the past period of time.

[0052] It's understandable that for the same task, different user accounts may have different completion and execution levels, and accordingly, different levels of participation in the task. Completion level represents the probability of a user account completing a task, which is related to the user account's historical task data; execution level represents the probability of a user account executing a task, which is related to the user account's historical task resource data; and participation level represents the probability of a user account participating in a task, which is related to the user account's probability of completing and executing the task.

[0053] Table 1 Participation of user accounts with different historical task volumes and historical task resource volumes in tasks

[0054] Large amount of historical mission resources Small amount of resources for historical missions Large amount of historical tasks High completion, low execution High completion and high execution Small amount of historical tasks Low completion and execution Low completion, high execution

[0055] Referring to the table above, the greater the amount of historical tasks, the greater the user account's ability to complete them. Therefore, for the same number of tasks, a user account with a greater amount of historical tasks will have a higher degree of task completion. Conversely, a user account with a smaller amount of historical tasks will have a lower degree of task completion. For the same amount of task resources, the greater the amount of historical task resources, the lower the probability of task completion for the user account. The smaller the amount of historical task resources, the higher the probability of task completion for the user account. For example, if historical task data is the number of likes on a user account's historical works posted on a social platform, and historical task resource data is the number of impressions of the user account's historical works posted on the social platform, the more likes a user account receives on its historical works on the social platform, the greater its ability to complete the like task assigned by the social platform. Therefore, for a task with the same number of likes, a user account with more likes on its historical works will have a higher degree of task completion. Conversely, a user account with fewer likes on its historical works will have a lower degree of task completion. For task resources with the same number of exposures, the more exposures a user account has of historical works published on social platforms, the lower the probability that the user account will perform the task; the fewer exposures a user account has of historical works published on social platforms, the higher the probability that the user account will perform the task.

[0056] The higher the completion or execution rate of a user account, the higher the user account's participation in the task. The lower the completion or execution rate of a user account, the lower the user account's participation in the task. In other words, user accounts with a small amount of historical tasks and a large amount of historical task resources have the lowest participation in the task, while user accounts with a large amount of historical tasks and a small amount of historical task resources have the highest participation in the task.

[0057] Since different user accounts have different historical task data and historical task resource data, the user accounts have different degrees of participation in tasks. In an embodiment of the present application, multiple user accounts can be clustered based on the historical task data of multiple user accounts to which tasks are to be issued and the corresponding historical task resource data, thereby obtaining at least one user account group, and then determining the target task data for each user account in each user account group.

[0058] In an exemplary embodiment, multiple user accounts can be clustered using a k-means clustering algorithm, and combined with the elbow method, an appropriate number of categories can be selected to obtain at least one user account group, wherein the completion and execution degrees of the user accounts in each user account group for the same task are the same or the difference is less than a preset threshold.

[0059] It is understood that the historical task data and corresponding historical task resource data of multiple user accounts to which tasks are to be assigned may contain abnormal data. In an exemplary embodiment, the abnormal data can be removed, and then the multiple user accounts can be clustered based on the remaining historical task data and corresponding historical task resource data. The abnormal data can be data that is significantly different from the historical task data and corresponding historical task resource data of other user accounts.

[0060] For example, still taking the task of liking works published on social platforms as an example, the average value a and variance b of the likes of historical works of multiple user accounts can be determined based on the likes of historical works of multiple user accounts, and the likes of historical works exceeding a+2b can be determined as abnormal data. Then, the likes of historical works of user accounts with likes less than a+2b and the corresponding exposure number can be used to cluster user accounts.

[0061] It should be noted that in the embodiments of the present application, the historical task data, historical task resource data and other data used may be normalized data.

[0062] In step 102 , a target task increase for each user account group is determined based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data.

[0063] The target task growth rate is the growth ratio of the target task relative to the historical task data. For example, taking the task of liking works published on a social platform as an example, if the total number of likes for the historical works of each user in the user account group is 1000, and the target task requires the total number of likes for the historical works of each user in the user group to reach 1200, then the target task growth rate for this user group is 0.2.

[0064] In step 103 , for each user account, target task data of the user account is determined based on the historical task data of the user account and the target task increment of the user account group to which it belongs.

[0065] In step 104, the target task is issued to the user account according to the target task data of the user account.

[0066] In an exemplary embodiment, the target task increase of each user account group can be determined based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data. Then, for each user account, the target task data of the user account can be determined based on the historical task data of the user account and the target task increase of the user account group to which it belongs. In this way, the target task can be issued to each user account according to the target task data of each user account.

[0067] By clustering multiple user accounts based on their historical task data and corresponding historical task resource data, at least one user account group is obtained, and a target task increase is determined for each user account group based on the historical task data and corresponding historical task resource data of the user accounts in each user account group, so that a matching target task increase can be determined for each user account group, and then, for each user account, the target task data of the user account is determined based on the historical task data of the user account and the target task increase of the user account group to which it belongs, and then the target task is issued to the user account according to the target task data of the user account, so that matching target task data can be determined for each user account in each user account group, thereby being able to issue appropriate tasks to each user account, realizing personalized task issuance to user accounts, and improving the matching degree between user accounts and tasks.

[0068] The following combination Figure 2 , the process of determining the target task increase of each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data in the embodiment of the present application is described.

[0069] Figure 2 The figure is a flowchart showing another method for issuing tasks according to an exemplary embodiment.

[0070] like Figure 2As shown above Figure 1 Step 102 in the example may specifically include the following steps 201 to 203. It should be noted that the embodiment of the present application is described by taking the task of liking a work published on a social platform as an example.

[0071] In step 201, the historical task data of the user accounts in each user account group and the corresponding historical task resource data are input into the task model to obtain the output value of the task model; wherein, the task model uses the task increase and task resource ratio of each user account group as model parameters, and the task model determines the task participation of each user account group based on the historical task data of the user accounts in each user account group, the corresponding historical task resource data, the task increase and task resource ratio of each user account group, and outputs the output value based on the task participation of each user account group and the task resource ratio of each user account group.

[0072] In step 202 , the task increment is adjusted within a first preset range and the task resource ratio is adjusted within a second preset range so that the output value of the task model reaches a maximum value.

[0073] In step 203 , the task increase when the output value of the task model reaches the maximum value is determined as the target task increase, and the task resource ratio when the output value of the task model reaches the maximum value is determined as the target task resource ratio.

[0074] The target task increment is the growth ratio of the target task relative to historical task data. The target task resource ratio is the ratio of the target task increment value to the target task resources. The target task increment can be calculated based on historical task data and the target task increment.

[0075] For example, taking the task of liking works published on social platforms as an example, assuming that the total number of likes for the historical works of each user in the user account group is 1000, and the target task requires that the total number of likes for the historical works of each user in the user group reaches 1200, then the target task increase for the user group is 0.2, and the target task increment is 1000*0.2=200.

[0076] The first preset range is the range within which each user account group's target task increase must meet, and the second preset range is the range within which each user account group's target task resource ratio must meet. The first and second preset ranges can be pre-set by the task issuer, such as an internet product or social platform, as needed, or can be set by other means, and this application does not impose any restrictions on this.

[0077] In an exemplary embodiment, a task model can be pre-built, using the task growth rate and task-to-resource ratio of each user account group as model parameters. The task model inputs the historical task data and corresponding historical task resource data of the user accounts in each user account group, and outputs a specific numerical value. Specifically, the task model can determine the task participation level of each user account group based on the historical task data, corresponding historical task resource data, task growth rate, and task-to-resource ratio of each user account group, and output an output value based on the task participation level of each user account group and the task-to-resource ratio of each user account group.

[0078] In an exemplary embodiment, the historical task data and corresponding historical task resource data of the user accounts in each user account group can be input into a pre-built task model to obtain the output value of the task model, and the task increase can be adjusted within a first preset range and the task resource ratio can be adjusted within a second preset range so that the output value of the task model reaches a maximum value. The task increase when the output value of the task model reaches the maximum value is then determined as the target task increase, and the task resource ratio when the output value of the task model reaches the maximum value is determined as the target task resource ratio. In this way, the target task increase for each user account group can be determined.

[0079] It should be noted that in the embodiment of the present application, the first preset range that the target task increase of each user account group needs to meet can be the same or different, and the second preset range that the target task resource ratio of each user account group needs to meet can be the same or different. This application does not impose any restrictions on this.

[0080] For example, the first preset range that the target task increase of user account group A meets can be preset to 0.1-0.3, the second preset range that the target task resource ratio of user account group A meets can be preset to 1.1-1.2, the first preset range that the target task increase of user account group B meets can be preset to 0.1-0.4, the second preset range that the target task resource ratio of user account group B meets can be preset to 1.1-1.3, and the preset step size is 0.01. After inputting the historical task data and corresponding historical task resource data of the user accounts in user account groups A and B into the task model, the task increase of user account group A in the model parameters can be adjusted within the range of 0.1-0.3, the task resource ratio of user account group A in the model parameters can be adjusted within the range of 1.1-1.2, the task increase of user account group B in the model parameters can be adjusted within the range of 0.1-0.4, and the task resource ratio of user account group B in the model parameters can be adjusted within the range of 1.1-1.3, so that the output value of the task model reaches the maximum value. Then, the task increase of user account group A when the output value of the task model reaches the maximum value is determined as the target task increase of user account group A, the task increase of user account group B when the output value of the task model reaches the maximum value is determined as the target task increase of user account group B, the task resource ratio of user account group A when the output value of the task model reaches the maximum value is determined as the target task resource ratio of user account group A, and the task resource ratio of user account group B when the output value of the task model reaches the maximum value is determined as the target task resource ratio of user account group B.

[0081] In summary, by pre-constructing a task model, inputting the historical task data of the user accounts in each user account group and the corresponding historical task resource data into the task model, and adjusting the task increment within the first preset range and the task resource ratio within the second preset range, the task increment when the output value of the task model reaches the maximum value is determined as the target task increment, and the task resource ratio when the output value of the task model reaches the maximum value is determined as the target task resource ratio, thereby achieving the goal of determining a matching target task increment for each user account group. In addition, since the target task increment and the target task resource ratio can be set in advance according to needs, and then the final target task increment and target task resource ratio are selected from the preset range, for Internet products or social platforms, by setting the target task resource ratio within a range greater than 1, it can be ensured that when the target task and the corresponding target task resources determined by this application are issued to the user account and the corresponding target task resources are issued, the ratio of the task reward obtained by the Internet product or social platform to the amount of task resources invested is greater than 1, thereby ensuring the quality of the user account's completion of the tasks issued by the Internet product or social platform.

[0082] The following combination Figure 3, the manner in which the task model outputs output values after inputting historical task data and corresponding historical task resource data of user accounts in each user account group into the task model in the embodiment of the present application is described.

[0083] Figure 3 The figure is a flowchart showing another method for issuing tasks according to an exemplary embodiment.

[0084] like Figure 3 As shown above Figure 2 Step 201 in the example may specifically include the following steps 301 to 308. It should be noted that the embodiment of the present application is described by taking the task of liking a work published on a social platform as an example.

[0085] In step 301 , for each user account in each user account group, a task increment for the user account is determined based on the historical task data of the user account, the task increment of the user account group to which the user account belongs, and the historical task data of each user account in the user account group.

[0086] It is understandable that, for a user account group, if the target task increase of the user account group is directly used to determine the target task data of all user accounts in the user account group, it may be unfair to some user accounts.

[0087] For example, taking the task of liking works published on a social platform as an example, assuming that the user account group includes user account 1 and user account 2, the number of likes for user account 1's works in the past week is 100, and the number of likes for user account 2's works in the past week is 10,000, and the target task increase of the user account group is 10%. If the target task increase of the user account group is used to determine the target task data corresponding to user account 1 and user account 2 respectively, then the target task data of user account 1 includes obtaining 110 likes, and the target task data of user account 2 includes obtaining 11,000 likes. Obviously, the difficulty of completing the target task data of user account 1 is much less than the difficulty of completing the target task data of user account 2.

[0088] In an embodiment of the present application, in order to ensure that the difficulty of completing the target task data is the same for each user account, after the historical task data of the user accounts in each user account group and the corresponding historical task resource data are input into the task model, for each user account in each user account group, the task increase rate of the user account group can be smoothly adjusted based on the historical task data of the user account, the task increase rate of the user account group to which the user account belongs, and the historical task data of each user account in the user account group to determine the task increase rate of each user account.

[0089] Specifically, when smoothly adjusting the task increase rate of a user account group, the historical task data of each user account in the user account group can be normalized first to obtain the normalized historical task data of each user account in the user account group. Then, based on the normalized historical task data of each user account in the user account group, the average historical task data of the user account group can be determined. Then, for each user account in the user account group, the task increase rate of the user account can be determined based on the normalized historical task data of the user account, the average historical task data of the user account group, and the task increase rate of the user account group.

[0090] In an exemplary embodiment, the historical task data of each user account in the user account group may be normalized in the manner shown in the following formula (1).

[0091]

[0092] Among them, X ij is the normalized historical task data of the jth user account in the i-th user account group, ∑L ij is the historical task data of the jth user account in the i-th user account group. In one embodiment, the historical task data is the task data of the user account in the past period of time, and ∑Lij is the total number of likes for the works of the jth user account in the i-th user account group in the past week.

[0093] Taking the task of liking works published on social platforms as an example, ∑L ij The total number of likes for the works of the jth user account in the i-th user account group in the past week can be determined by formula (1): ij .

[0094] In an exemplary embodiment, the task increase of the user account can be determined for each user account in each user account group according to the historical task data of the user account, the task increase of the user account group to which the user account belongs, and the historical task data of each user account in the user account group in the manner shown in the following formula (2).

[0095]

[0096] Among them, T ij is the task increment of the jth user account in the i-th user account group, X ij is the normalized historical task data of the jth user account in the i-th user account group, T i is the task increment of the i-th user account group, is the average historical task data of the i-th user account group. m is the number of user accounts in the i-th user account group.

[0097] Taking the task of liking works published on social platforms as an example, X ij For ∑L ij The total number of likes for the work after normalization, is the average value of the total number of likes for all user accounts in the i-th user account group after normalization, T i is the average increase in the number of likes for the works of the i-th user account group. According to the above formula (2), the increase in the number of likes for the works of the j-th user account in the i-th user account group can be determined as T ij .

[0098] For example, suppose the task increase of a certain user account group is 0.2, where the total number of likes for user account 1's works in the past week is 10, and the total number of likes for user account 2's works in the past week is 100. Then, through the processing of the above formulas (1) and (2), it can be obtained that the task increase of user account 1 is 0.3, and the task increase of user account 2 is 0.1. However, overall, the task increase of this user account group is still 0.2.

[0099] Through the above process, it is possible to determine the task increase of each user account in the user account group based on the task increase of the user account group for each user account group, and overall, the task increase of the user account group remains unchanged, so that the target task data of each user account can be determined based on the task increase of each user account in the future, and for each user account, the difficulty of completing the target task data is the same.

[0100] In step 302 , a task increment corresponding to the task increment of the user account is determined based on the historical task data of the user account and the task increment of the user account.

[0101] In an exemplary embodiment, the task increment corresponding to the task increase of the user account can be determined according to the historical task data of the user account and the task increase of the user account in the form shown in the following formula (3).

[0102] L' ij =∑L ij *T ij (3)

[0103] Among them, ∑L ij is the historical task data of the jth user account in the i-th user account group, T ij is the task increment of the jth user account in the i-th user account group, L' ijThe task increment corresponding to the task increment of the j-th user account in the i-th user account group.

[0104] Taking the task of liking works published on social platforms as an example, suppose the total number of likes for works by the jth user account in the i-th user account group in the past week is ∑L ij is 200, the target task increase of the jth user account in the i-th user account group is T ij If it is 20%, then the increment of the number of likes for the work of the jth user account in the i-th user account group can be determined as L' ij is 40.

[0105] In step 303 , task resource data corresponding to the task increase of the user account is determined based on the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs.

[0106] In an exemplary embodiment, the task resource data corresponding to the task increase of the user account can be determined according to the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs in the form shown in the following formula (4).

[0107]

[0108] Among them, L' ij is the task increment corresponding to the task increment of the jth user account in the i-th user account group, ROI i is the task resource ratio of the i-th user account group, R ij is the task resource data corresponding to the task increment of the jth user account in the i-th user account group, and c is the value coefficient corresponding to the task increment corresponding to the task increment. The value of c can be set as needed.

[0109] Taking the task of liking works published on social platforms as an example, assuming that the number of likes for the works published by the user account is the user task, and the number of exposures of the works published by the social platform to the user account is the task resource, then c can be the number of exposures corresponding to the value of 1 like, and L' ij The increment of the number of likes for the work of the jth user account in the i-th user account group, R ij The number of exposures of the work rewarded to the jth user account in the i-th user account group after completing the like task. Assuming the value of c is 2.2, the increment of the number of likes of the work of the jth user account in the i-th user account group is L' ij is 40, the target task resource ratio ROI of the i-th user account group i If it is 1.1, then the task resource data corresponding to the task increase of the user account can be determined as 80 by the above formula (4).

[0110] In step 304 , the task execution degree of the user account for the task increment is obtained based on the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account.

[0111] Among them, the task execution degree represents the probability of a user account executing a task.

[0112] In an exemplary embodiment, the task execution degree of the user account for the task increment can be a first value or a second value. The first value is a non-zero value, indicating that the probability of the user account executing the task is not zero; the second value is 0, indicating that the probability of the user account executing the task is zero.

[0113] In an exemplary embodiment, the task execution degree of the user account for the task increment can be obtained by determining whether the ratio of the task resource data corresponding to the task increment of the user account to the historical task resource data corresponding to the historical task data of the user account is greater than a preset value. Wherein, if the ratio of the task resource data corresponding to the task increment of the user account to the historical task resource data of the user account is greater than the preset value, the task execution degree of the user account for the task increment is determined to be a first value; if the ratio of the task resource data corresponding to the task increment of the user account to the historical task resource data of the user account is less than or equal to the preset value, the task execution degree of the user account for the task increment is determined to be a second value.

[0114] Among them, the preset value can be set as needed in the actual application scenario, and this application does not impose any restrictions on this.

[0115] Taking the task of liking works published on social platforms as an example, the task execution degree of the user account to the task increase can be determined by the following formula (5).

[0116]

[0117] Among them, F ij R is the task execution degree of the jth user account in the i-th user account group for the task increment. ij W is the number of exposures of works awarded to the jth user account in the ith user account group after completing the like task. ij N1 is the number of exposures of the works of the jth user account in the i-th user account group over the past period. For example, it is the average number of exposures of the works produced by the jth user account in the i-th user account group over the past week within 12 hours after release. N1 is a non-zero value.

[0118] In the above formula (5), 1-E i This is the preset value mentioned in the embodiment of this application, where E iThe probability of the i-th user account group acquiring the task resource data corresponding to the task increase can be determined based on the proportion of user accounts in the user account group that have purchased traffic in the past period of time, relative to the total number of user accounts in the group. Traffic can be, for example, the number of followers. For example, if 80% of the user accounts in the i-th user account group have purchased followers in the past week, then E i is 80%.

[0119] In practical applications, E can be adjusted as needed i For example, if we do not want 1-E i When it is less than 50%, the minmax method can be used to map the proportion of user accounts that have purchased fans (80%) to the interval [0, 0.5], that is, E i Adjusted to 40%, so that 1-E i is 60%.

[0120] Furthermore, according to the above formula (5), when the ratio of the number of exposures of works rewarded to the jth user account in the i-th user account group after completing the like task to the average number of exposures of works produced by the jth user account in the i-th user account group in the past week within 12 hours after release is greater than 60%, the task execution degree of the user account for the task increase is N1; when the ratio of the number of exposures of works rewarded to the jth user account in the i-th user account group after completing the like task to the average number of exposures of works produced by the jth user account in the i-th user account group in the past week within 12 hours after release is not greater than 60%, the task execution degree of the user account for the task increase is 0.

[0121] In step 305, the task completion degree of the user account for the task increment is obtained based on the historical task data of the user account.

[0122] Among them, task completion represents the probability of a user account completing a task.

[0123] In an exemplary embodiment, the probability distribution to which the historical task data of the user account belongs can be determined based on the historical task data of the user account, and then the task completion degree of the user account for the target incentive task can be obtained based on the probability distribution.

[0124] Specifically, when the probability distribution of the historical task data of the user account is a normal distribution, the task completion degree of the user account for the target increase can be determined based on the mean and variance of the normal distribution.

[0125] The following uses the task of liking works published on social platforms as an example to illustrate the process of obtaining the task completion degree of a user account based on the historical task data of the user account.

[0126] Assume that the historical task count of the jth user account in the i-th user account group includes the historical like count of all works of the user account, where the total like count of all works of the user account in the past week ∑L ij , assuming that the user account has published M works in the past week, the average number of likes for these works is Then the following formula (6) can be obtained.

[0127]

[0128] Assuming that the number of works published by the user account remains unchanged, that is, M is a constant, the process of determining the probability distribution of the total number of historical likes for all works of the user account can be transformed into determining the average number of likes for all works of the user account in the past week The process of probability distribution.

[0129] In this embodiment of the present application, the average number of likes for all works of the user account in the past week can be determined by Monte Carlo simulation. The probability distribution of .

[0130] Specifically, suppose the sequence of the number of likes for each work of the jth user account in the i-th user account group in the past week is L ij , where L ij The sequence length is M, that is, L ij The length of the sequence is the number of works published by the jth user account in the i-th user account group in the past week, which can be obtained by replacing the sequence L ij We extract k times and get k iid (independent identically distributed) variable sequences, where each variable sequence {L ijk} are all the same length as L ij The length of is the same, which is a constant M, and then the mean of these k variable sequences is obtained respectively.

[0131] According to the central limit theorem, the mean of each of these k iid variable sequences is Together they form a normal distribution, and the mean of this normal distribution is the original sequence L ij The mean An unbiased estimate of Normal distribution Among them, μ ij is the mean of the normal distribution, σ ij is the variance of the normal distribution. Among them, mean represents the variable sequence {L ijk The mean of The average value, std means the variable sequence {L ijk The mean of The standard deviation of .

[0132] After determining the normal distribution to which the historical task data of the user account belongs, the target task can be determined based on the historical task data of the user account and the task increase of the user account. Since for any target task, the probability corresponding to the target task can be inferred by calculating the position of the target task in the normal distribution, the task completion degree of the user account for the task increase can be determined based on the probability corresponding to the target task.

[0133] refer to Figure 4 The average number of likes for all works of the jth user account in the i-th user account group in the past week Normal distribution diagram, in determining the average number of likes for all works of the jth user account in the i-th user account group in the past week After the probability distribution of Figure 4 Assume that Figure 4 The intersection indicated by the arrow is the location of the target task, and the task completion degree of the user account to the task increase can be calculated by the following formula (7).

[0134]

[0135] Among them, C ij is the task completion degree of the user account for the task increment, μ ij is the mean of the normal distribution, T ij is the task increment of the jth user account in the i-th user account group, is the average number of likes for all works of the jth user account in the i-th user account group in the past week. ij It is a value between [0,1]. express probability.

[0136] In step 306 , the task participation level of the user account is determined based on the task execution level and the task completion level.

[0137] It can be understood that the task execution degree of the user account for the task increment can be a first value or a second value, wherein the first value is a non-zero value, indicating that the probability of the user account executing the task is not 0; the second value is 0, indicating that the probability of the user account executing the task is 0.

[0138] In an exemplary embodiment, when the task execution degree of the user account for the task increment is a first value, the task completion degree of the user account for the task increment can be determined as the task participation degree of the user account; when the task execution degree of the user account for the task increment is a second value, the task participation degree of the user account can be determined to be 0. That is, the task participation degree of each user account in each user account group can be determined by the method shown in the following formula (8).

[0139]

[0140] Among them, P ij is the task participation of the jth user account in the i-th user account group, C ij F is the task completion degree of the jth user account in the i-th user account group for the task increment, ij is the task execution degree of the jth user account in the i-th user account group for the task increment, and N1 is a first value.

[0141] Through the above process, it is possible to determine the task participation of each user account in each user account group based on the historical task data of the user accounts in each user account group, the corresponding historical task resource data, and the task increase and task resource ratio in the group for each group of tasks.

[0142] In step 307 , the task participation degree of each user account group is determined based on the task participation degree of each user account in each user account group.

[0143] It can be understood that, for each group of task increases and task resource ratios, after determining the task participation of each user account in each user account group based on the historical task data of the user accounts in each user account group, the corresponding historical task resource data, and the task increase and task resource ratio in the group, the task participation of the user account group can be determined based on the task participation of each user account in the user account group.

[0144] In an exemplary embodiment, for each user account group, the task engagement level of each user account group can be determined by taking the average of the task engagement levels corresponding to all user accounts in the user account group. That is, the task engagement level of each user account group can be determined using the following formula (9).

[0145]

[0146] Among them, P i is the task participation of the i-th user account group, P ij is the task participation of the jth user account in the i-th user account group, and m is the number of user accounts in the i-th user account group.

[0147] In step 308 , an output value of the task model is output according to the task participation degree of each user account group and the task resource ratio of each user account group.

[0148] In an exemplary embodiment, after determining the task participation of each user account group according to the task participation of each user account in each user account group, the output value P' of the task model can be determined by the following formula (10).

[0149]

[0150] Among them, ROI i is the target task resource ratio of the i-th user account group, P i is the task participation of the i-th user account group, and n is the number of user account groups.

[0151] Through the above process, after the historical task data of the user accounts in each user account group and the corresponding historical task resource data are input into the task model, the output value of the task model can be obtained.

[0152] The following combination Figure 5 , further explains the task issuing method provided in the embodiment of the present application.

[0153] Figure 5 The figure is a flowchart showing another method for issuing tasks according to an exemplary embodiment.

[0154] like Figure 5 As shown, the task issuing method may specifically include the following steps 501-507.

[0155] In step 501 , multiple user accounts are clustered based on their historical task data and corresponding historical task resource data to obtain at least one user account group.

[0156] In step 502 , a target task increase for each user account group is determined based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data.

[0157] The specific implementation process and principle of the above steps 501-502 can be referred to the description of the above embodiment and will not be repeated here.

[0158] In step 503 , for each user account, the target task increase of the user account is determined based on the historical task data of the user account, the target task increase of the user account group to which it belongs, and the historical task data of each user account in the user account group.

[0159] In an exemplary embodiment, after determining the target task increase for each user account group, the target task increase for each user account in each user account group can be determined for each user account based on the historical task data of the user account, the target task increase for the user account group to which it belongs, and the historical task data of each user account in the user account group, using the method shown in the above formulas (1) and (2).

[0160] In step 504 , target task data of the user account is determined based on the historical task data of the user account and the target task increment of the user account.

[0161] In an exemplary embodiment, the target task data of the user account can be determined according to the historical task data of the user account and the target task increase of the user account in the manner shown in formula (11).

[0162] X i ' j =X ij (1+T ij ) (11)

[0163] Among them, X i ' j is the target task data of the jth user account in the i-th user account group, X ij is the normalized historical task data of the jth user account in the i-th user account group, T ij is the target task increase of the jth user account in the i-th user account group.

[0164] Specifically, the target task increase and historical task data of the jth user account in the i-th user account group are substituted into the above formula (11) to determine the target task data of the jth user account in the i-th user account group.

[0165] In step 505 , the target task is issued to the user account according to the target task data of the user account.

[0166] In step 506 , target task resource data of the user account is determined based on the historical task data of the user account, the target task increase of the user account, and the target task resource ratio of the user account.

[0167] In step 507 , when it is determined that the client of the logged-in user account has completed the target task data, the corresponding target task resources are issued to the client according to the target task resource data of the user account.

[0168] Among them, step 506 can be executed after step 505, or before step 505, or simultaneously with step 505, and this application does not impose any restrictions on this.

[0169] In an exemplary embodiment, for each user account, the historical task data of the user account, the target task increase rate of the user account, and the target task resource ratio are substituted into formulas (3) and (4) to determine the target task resource data of the user account.

[0170] Specifically, after determining the target task data of each user account, the target task can be issued to each user account according to the target task data of each user account. After determining the target task resource data of each user account, when it is determined that the client logged into each user account has completed the target task data, the corresponding target task resources can be issued to each client according to the target task resource data of each user account.

[0171] It can be understood that the target task increase and target task resource ratio for each user account group determined in the present application are a set of optimal model parameters when the output value of the task model reaches the maximum value. Since the output value of the task model reaches the maximum value, the benefit of the task publisher, such as a social platform, is maximized. Therefore, by using the target task increase and target task resource ratio for each user account group determined by the task issuance method of the present application, the target task data and corresponding target task resource data of each user account are determined and issued, which can maximize the platform's benefits.

[0172] In addition, since the embodiment of the present application determines a suitable target task increment for each user account, and then determines the target task data and corresponding target task resource data for each user account based on the target task increment for each user account, the target task data and corresponding target task resource data for each user account are customized for it and most suitable for the user account. Moreover, since the target task data is set for each user account based on the target task increment for the user account, when setting the target task data, the target task data for each user account can be set higher than the historical task data, thereby ensuring that the ROI of the task publisher, such as a social platform, is greater than 1, thereby ensuring the revenue of the task publisher, such as a social platform.

[0173] In order to implement the above embodiment, the embodiment of the present disclosure proposes a task issuing device.

[0174] Figure 6 It is a block diagram of a task issuing apparatus according to an exemplary embodiment.

[0175] Reference Figure 6 The task issuing device 600 may include: a clustering module 601 , a first determining module 602 , a second determining module 603 and a first issuing module 604 .

[0176] The clustering module 601 is configured to cluster the multiple user accounts based on the historical task data and the corresponding historical task resource data of the multiple user accounts to obtain at least one user account group;

[0177] A first determining module 602 is configured to determine a target task increase for each user account group based on historical task data of user accounts in each user account group and corresponding historical task resource data;

[0178] The second determining module 603 is configured to determine the target task data of each user account based on the historical task data of the user account and the target task increment of the user account group to which it belongs;

[0179] The first issuing module 604 is configured to issue the target task to the user account according to the target task data of the user account.

[0180] It should be noted that the task issuing device of the embodiment of the present disclosure can execute the task issuing method in the aforementioned embodiment. The task issuing device can be an electronic device or can be configured in an electronic device to determine and issue tasks matching user accounts to multiple user accounts.

[0181] The electronic device can be any stationary or mobile computing device with a display screen that can install software products or run web products and perform data processing, such as mobile computing devices such as laptops, smartphones, and wearable devices, or stationary computing devices such as desktop computers, or other types of computing devices. The task issuing device can be an application installed on the electronic device or a software management tool for software products or web products, and the embodiments of the present disclosure are not limited thereto.

[0182] In a possible implementation form, the first determining module 602 includes:

[0183] an acquisition unit configured to input historical task data and corresponding historical task resource data of user accounts in each user account group into a task model to acquire an output value of the task model; wherein the task model uses the task increase rate and task resource ratio of each user account group as model parameters, and the task model determines the task participation degree of each user account group based on the historical task data of the user accounts in each user account group, the corresponding historical task resource data, the task increase rate and task resource ratio of each user account group, and outputs an output value based on the task participation degree of each user account group and the task resource ratio of each user account group;

[0184] An adjusting unit is configured to adjust the task increment within a first preset range and adjust the task resource ratio within a second preset range so that the output value of the task model reaches a maximum value;

[0185] The first determining unit is configured to determine the task increase when the output value of the task model reaches a maximum value as the target task increase, and determine the task resource ratio when the output value of the task model reaches a maximum value as the target task resource ratio.

[0186] In another possible implementation form, the acquiring unit is specifically configured to execute:

[0187] For each group of task increase and task resource ratio, determine the task participation of each user account in each user account group based on the historical task data of the user accounts in each user account group, the corresponding historical task resource data, and the task increase and task resource ratio in the group;

[0188] Determining the task participation level of each user account group based on the task participation level of each user account in each user account group;

[0189] Output the output value of the task model based on the task participation of each user account group and the task resource ratio of each user account group.

[0190] In another possible implementation form, the acquiring unit is specifically configured to execute:

[0191] For each user account in each user account group, determine a task increment for the user account based on the historical task data of the user account, the task increment of the user account group to which the user account belongs, and the historical task data of each user account in the user account group;

[0192] Determine the task increment corresponding to the task increment of the user account based on the historical task data of the user account and the task increment of the user account;

[0193] Determining task resource data corresponding to the task increase of the user account based on the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs;

[0194] Obtaining the task execution degree of the user account for the task increase based on the task resource data corresponding to the task increase of the user account and the historical task resource data corresponding to the historical task data of the user account;

[0195] Based on the historical task data of the user account, obtain the task completion degree of the user account for the task increment;

[0196] Determine the task participation of the user account based on the task execution degree and task completion degree.

[0197] In another possible implementation form, the acquiring unit is specifically configured to execute:

[0198] Determine the normal distribution of the historical task data of the user account based on the historical task data of the user account;

[0199] Determine the task completion degree of the user account for the task increment based on the mean and variance of the normal distribution.

[0200] In another possible implementation form, the acquiring unit is specifically configured to execute:

[0201] When the ratio of the task resource data to the historical task resource data is greater than a preset value, determining the task execution degree to be a first value;

[0202] When the ratio of the task resource data to the historical task resource data is less than or equal to a preset value, the task execution degree is determined to be a second value.

[0203] In another possible implementation, the task execution degree of the task increment of the user account is a first value or a second value;

[0204] The acquisition unit is specifically configured to perform:

[0205] When the task execution degree of the user account for the task increment is a first value, determining the task completion degree of the user account for the task increment as the task participation degree of the user account;

[0206] When the task execution degree of the user account for the task increment is a second value, the task participation degree of the user account is determined to be 0.

[0207] In another possible implementation, the second determining module 603 includes:

[0208] a second determining unit configured to determine, for each user account, a target task increase of the user account based on historical task data of the user account, a target task increase of the user account group to which it belongs, and historical task data of each user account in the user account group;

[0209] The third determining unit is configured to determine the target task data of the user account according to the historical task data of the user account and the target task increase of the user account.

[0210] In another possible implementation, the task issuing device 600 further includes:

[0211] a third determining module configured to determine target task resource data of the user account based on historical task data of the user account, a target task increase rate of the user account, and a target task resource ratio of the user account;

[0212] The second issuing module is configured to issue corresponding target task resources to the client according to the target task resource data of the user account when it is determined that the client of the logged-in user account has completed the target task data.

[0213] It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0214] The task issuing device of the disclosed embodiment first clusters multiple user accounts based on their historical task data and corresponding historical task resource data to obtain at least one user account group, and then determines the target task increase of each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data. Then, for each user account, the target task data of the user account is determined based on the historical task data of the user account and the target task increase of the user account group to which it belongs, and then the target task is issued to the user account according to the target task data of the user account. In this way, appropriate tasks can be issued to each user account, realizing personalized task issuance to user accounts and improving the matching degree between user accounts and tasks.

[0215] In order to implement the above embodiments, the present disclosure further provides an electronic device.

[0216] The electronic device 700 includes:

[0217] Processor 720;

[0218] a memory 710 for storing instructions executable by a processor 720;

[0219] The processor 720 is configured to execute instructions to implement the task issuing method as described above.

[0220] As an example, Figure 7 is a block diagram of an electronic device 700 for issuing tasks according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may further include:

[0221] The memory 710 and the processor 720, a bus 730 connecting different components (including the memory 710 and the processor 720), the memory 710 stores a computer program, and when the processor 720 executes the program, the task dispatching method described in the embodiment of the present disclosure is implemented.

[0222] Bus 730 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0223] The electronic device 700 typically includes a variety of electronic device-readable media, which can be any available media that can be accessed by the electronic device 700, including volatile and non-volatile media, removable and non-removable media.

[0224] The memory 710 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 740 and / or cache memory 750. The electronic device 700 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 760 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 Not shown, often called a "hard drive"). Although Figure 7 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 730 via one or more data medium interfaces. Memory 710 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present disclosure.

[0225] A program / utility 780 having a set (at least one) of program modules 770 may be stored, for example, in memory 710. Such program modules 770 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 770 generally implement the functions and / or methods of the embodiments described herein.

[0226] The electronic device 700 may also communicate with one or more external devices 790 (e.g., a keyboard, a pointing device, a display 791, etc.), and may also communicate with one or more devices that enable a user account to interact with the electronic device 700, and / or any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 792. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 793. Figure 7 As shown, the network adapter 793 communicates with other modules of the electronic device 700 via the bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0227] The processor 720 executes various functional applications and data processing by running programs stored in the memory 710 .

[0228] It should be noted that the implementation process and technical principles of the electronic device of this embodiment can be found in the aforementioned explanation of the task issuing method of the embodiment of the present disclosure, and will not be repeated here.

[0229] The electronic device provided by the embodiment of the present disclosure first clusters multiple user accounts based on the historical task data of the multiple user accounts and the corresponding historical task resource data to obtain at least one user account group, and then determines the target task increase of each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data. Then, for each user account, the target task data of the user account is determined based on the historical task data of the user account and the target task increase of the user account group to which it belongs, and then the target task is issued to the user account according to the target task data of the user account. In this way, appropriate tasks can be issued to each user account, realizing personalized task issuance to user accounts and improving the matching degree between user accounts and tasks.

[0230] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 710 including instructions, and the instructions can be executed by a processor 720 of the electronic device 700 to perform the above method. Alternatively, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0231] In an exemplary embodiment, a computer program product is further provided, including a computer program, wherein when the computer program is executed by a processor, the task issuing method as described above is implemented.

[0232] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0233] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A task issuing method, characterized in that: include: Clustering the multiple user accounts based on historical task data and corresponding historical task resource data to obtain at least one user account group, wherein the historical task resource data is task resource data obtained after the users completed tasks within a past period of time; Determine the target task increase for each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data; For each user account, determining target task data for the user account based on the historical task data of the user account and the target task increment of the user account group to which the user account belongs; According to the target task data of the user account, the target task is issued to the user account; Determining the target task increase for each user account group based on the historical task data of the user accounts in each user account group and the corresponding historical task resource data includes: Inputting historical task data and corresponding historical task resource data of user accounts in each of the user account groups into a task model to obtain an output value of the task model; wherein the task model uses the task increment and task-resource ratio of each of the user account groups as model parameters, and the task model determines the task participation of each of the user account groups based on the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, the task increment and task-resource ratio of each of the user account groups, and outputs the output value based on the task participation of each of the user account groups and the task-resource ratio of each of the user account groups, where the task-resource ratio is the ratio of the value of the target task increment to the target task resource; Adjusting the task increment within a first preset range and adjusting the task resource ratio within a second preset range so that the output value of the task model reaches a maximum value; The task increase when the output value of the task model reaches the maximum value is determined as the target task increase, and the task resource ratio when the output value of the task model reaches the maximum value is determined as the target task resource ratio.

2. The task issuing method according to claim 1, characterized in that: The way in which the task model outputs the output value includes: For each group of task increases and task-resource ratios, determining the task participation of each user account in each of the user account groups based on historical task data of the user accounts in each of the user account groups, corresponding historical task resource data, and the task increases and task-resource ratios in each group; determining a task participation degree of each of the user account groups according to a task participation degree of each of the user accounts in each of the user account groups; An output value of the task model is outputted according to the task participation degree of each of the user account groups and the task resource ratio of each of the user account groups.

3. The task issuing method according to claim 2, characterized in that: The step of determining, for each group of task increments and task-resource ratios, the task participation level of each user account in each of the user account groups based on historical task data of the user accounts in each of the user account groups, corresponding historical task resource data, and the task increments and task-resource ratios in each group, includes: For each user account in each user account group, determining a task increment for the user account based on historical task data of the user account, a task increment for the user account group to which the user account belongs, and historical task data for each user account in the user account group; Determining a task increment corresponding to the task increment of the user account based on the historical task data of the user account and the task increment of the user account; determining task resource data corresponding to the task increase of the user account according to the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs; Obtaining a task execution degree of the user account for the task increment according to the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account; Obtaining, based on the historical task data of the user account, a task completion degree of the task increment by the user account; The task participation degree of the user account is determined according to the task execution degree and the task completion degree.

4. The task issuing method according to claim 3, characterized in that: The obtaining, based on the historical task data of the user account, the task completion degree of the task increment by the user account includes: Determining, based on the historical task data of the user account, a normal distribution to which the historical task data of the user account belongs; Determine the task completion degree of the user account for the task increment according to the mean and variance of the normal distribution.

5. The task issuing method according to claim 3, characterized in that: The obtaining, based on the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account, the task execution degree of the user account for the task increment includes: When the ratio of the task resource data to the historical task resource data is greater than a preset value, determining the task execution degree to be a first value; When the ratio of the task resource data to the historical task resource data is less than or equal to a preset value, the task execution degree is determined to be a second value.

6. The task issuing method according to claim 3, characterized in that: The task execution degree of the task increment by the user account is a first value or a second value; The determining, based on the task execution degree and the task completion degree, the task participation degree of the user account includes: When the task execution degree of the user account for the task increment is a first value, determining the task completion degree of the user account for the task increment as the task participation degree of the user account; When the task execution degree of the user account for the task increment is a second value, the task participation degree of the user account is determined to be 0.

7. The task issuing method according to any one of claims 1 to 6, characterized in that: The step of determining, for each user account, target task data of the user account based on the historical task data of the user account and the target task increment of the user account group to which the user account belongs includes: For each user account, determining the target task increase of the user account based on the historical task data of the user account, the target task increase of the user account group to which it belongs, and the historical task data of each user account in the user account group; The target task data of the user account is determined according to the historical task data of the user account and the target task increase of the user account.

8. The task issuing method according to claim 7, characterized in that: Also includes: determining target task resource data of the user account according to historical task data of the user account, target task increase of the user account, and target task resource ratio of the user account; When it is determined that the client logged into the user account completes the target task data, corresponding target task resources are issued to the client according to the target task resource data of the user account.

9. A task issuing device, characterized in that: include: a clustering module configured to cluster the multiple user accounts based on historical task data and corresponding historical task resource data of the multiple user accounts to obtain at least one user account group, wherein the historical task resource data is task resource data obtained after the users completed tasks within a past period of time; A first determining module is configured to determine a target task increase for each user account group based on historical task data of user accounts in each user account group and corresponding historical task resource data; a second determining module configured to determine, for each user account, target task data of the user account based on historical task data of the user account and a target task increment of a user account group to which the user account belongs; A first issuing module is configured to issue a target task to the user account according to the target task data of the user account; The first determining module includes: an acquiring unit configured to input historical task data and corresponding historical task resource data of user accounts in each of the user account groups into a task model to acquire an output value of the task model; wherein the task model uses the task increment and task-resource ratio of each of the user account groups as model parameters, and the task model determines the task participation of each of the user account groups based on the historical task data of the user accounts in each of the user account groups, the corresponding historical task resource data, the task increment and task-resource ratio of each of the user account groups, and outputs the output value based on the task participation of each of the user account groups and the task-resource ratio of each of the user account groups, wherein the task-resource ratio is a ratio of the value of the target task increment to the target task resource; An adjusting unit is configured to adjust the task increment within a first preset range and adjust the task resource ratio within a second preset range so that the output value of the task model reaches a maximum value; The first determining unit is configured to determine the task increase when the output value of the task model reaches the maximum value as the target task increase, and determine the task resource ratio when the output value of the task model reaches the maximum value as the target task resource ratio.

10. The task issuing device according to claim 9, characterized in that: The acquisition unit is specifically configured to execute: For each group of task increases and task-resource ratios, determining the task participation of each user account in each of the user account groups based on historical task data of the user accounts in each of the user account groups, corresponding historical task resource data, and the task increases and task-resource ratios in each group; determining a task participation degree of each of the user account groups according to a task participation degree of each of the user accounts in each of the user account groups; An output value of the task model is outputted according to the task participation degree of each of the user account groups and the task resource ratio of each of the user account groups.

11. The task issuing device according to claim 10, characterized in that: The acquisition unit is specifically configured to execute: For each user account in each user account group, determining a task increment for the user account based on historical task data of the user account, a task increment for the user account group to which the user account belongs, and historical task data for each user account in the user account group; Determining a task increment corresponding to the task increment of the user account based on the historical task data of the user account and the task increment of the user account; determining task resource data corresponding to the task increase of the user account according to the task increment corresponding to the task increase of the user account and the task resource ratio of the user account group to which the user account belongs; Obtaining a task execution degree of the user account for the task increment according to the task resource data corresponding to the task increment of the user account and the historical task resource data corresponding to the historical task data of the user account; Obtaining, based on the historical task data of the user account, a task completion degree of the task increment by the user account; The task participation degree of the user account is determined according to the task execution degree and the task completion degree.

12. The task issuing device according to claim 11, characterized in that: The acquisition unit is specifically configured to execute: Determining, based on the historical task data of the user account, a normal distribution to which the historical task data of the user account belongs; Determine the task completion degree of the user account for the task increment according to the mean and variance of the normal distribution.

13. The task issuing device according to claim 11, characterized in that: The acquisition unit is specifically configured to execute: When the ratio of the task resource data to the historical task resource data is greater than a preset value, determining the task execution degree to be a first value; When the ratio of the task resource data to the historical task resource data is less than or equal to a preset value, the task execution degree is determined to be a second value.

14. The task issuing device according to claim 11, characterized in that: The task execution degree of the task increment by the user account is a first value or a second value; The acquisition unit is specifically configured to execute: When the task execution degree of the user account for the task increment is a first value, determining the task completion degree of the user account for the task increment as the task participation degree of the user account; When the task execution degree of the user account for the task increment is a second value, the task participation degree of the user account is determined to be 0.

15. The task issuing device according to any one of claims 9 to 14, characterized in that: The second determining module includes: a second determining unit configured to determine, for each user account, a target task increase of the user account based on the historical task data of the user account, the target task increase of the user account group to which it belongs, and the historical task data of each user account in the user account group; The third determining unit is configured to determine the target task data of the user account according to the historical task data of the user account and the target task increase of the user account.

16. The task issuing device according to claim 15, characterized in that: Also includes: a third determining module configured to determine target task resource data of the user account based on historical task data of the user account, a target task increase rate of the user account, and a target task resource ratio of the user account; The second issuing module is configured to execute, when it is determined that the client that logs into the user account completes the target task data, issuing corresponding target task resources to the client according to the target task resource data of the user account.

17. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instruction to implement the task issuing method according to any one of claims 1 to 8.

18. A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to execute the task issuing method according to any one of claims 1 to 8.

19. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the task issuing method according to any one of claims 1 to 8 is implemented.

Images