CN115330434A

CN115330434A - Method for screening active target users and related equipment thereof

Info

Publication number: CN115330434A
Application number: CN202210837732.0A
Authority: CN
Inventors: 钱娟; 孙柯; 张国辉; 吴震操
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2022-07-15
Filing date: 2022-07-15
Publication date: 2022-11-11

Abstract

The embodiment of the application belongs to the field of big data, is applied to the technical field of intelligent screening of data analysis, and relates to a method for screening active target users, which comprises the steps of determining the target exposure per hour in each active stage through a preset algorithm model, performing activity pushing in each active stage based on the target exposure, obtaining pushing results in each active stage, and screening active primary users and active target users based on the pushing results, so that screening of the primary users in an active recommendation testing stage is realized, screening of the target users in an active recommendation promotion stage is realized, and further screening of the target users in an active recommendation optimization stage is realized.

Description

Method for screening active target users and related equipment thereof

Technical Field

The application relates to the technical field of big data and data analysis intelligent screening, in particular to a method for screening active target users and related equipment.

Background

The labels are description and depiction of a certain dimensional characteristic of an object, are symbolic representations of a certain user characteristic, each label defines an angle for observing and knowing the description object, are used for marking, depicting, classifying and extracting the characteristic of the object, have the classifiability, and are highly refined feature identifications which are set artificially and obtained by applying a certain algorithm to a target object according to the requirements of a service scene;

the label system classifies various labels required by enterprises and defines the label attributes simultaneously, so that the labels are more conveniently managed, maintained, applied and evaluated. The main two parts of the label system are a label classification system and label content information, and the label system can be maintained through the label system, the traditional label system is used for screening active target users and mostly adopts a single selection source, the rule configuration is not rich, and the user population screening is not careful.

Disclosure of Invention

The embodiment of the application aims to provide a method, a device, computer equipment and a storage medium for screening active target users, so that the target users can be screened accurately better after the activity is released.

In order to solve the above technical problem, an embodiment of the present application provides a method for screening a mobile target user, which adopts the following technical scheme:

a method for screening active target users comprises the following steps:

when entering a current activity stage, acquiring the remaining denomination, the remaining days and the preset duration of the activity stage, wherein the activity stage comprises the following steps: testing period, promotion period and optimization period;

acquiring a parameter value of a current activity stage, and based on a preset first algorithm formula:

determining the target exposure per hour in the current activity stage, wherein x is the remaining denomination of activity in the current activity stage, and d is the current activityThe number of the remaining days of the activity in the dynamic stage, p is a parameter value of the current activity stage, and h is a preset duration of the current activity stage;

performing activity pushing of each activity stage based on the target exposure, and acquiring pushing results of each activity stage;

and screening out the activity primary selection user and the activity target user based on the pushing result.

Further, the step of obtaining the push result of each activity stage specifically includes:

partitioning each activity recommendation subclass in an activity recommendation interface in advance, and setting an activity distinguishing label for each activity recommendation subclass;

based on a preset monitoring component, acquiring the total number of times that each activity recommendation subclass is pushed in each activity stage, the number of times that each activity recommendation subclass is clicked, a click user identifier when each activity recommendation subclass is clicked, a completion user identifier when a recommendation task of each activity recommendation subclass is completed, and a comment user identifier when each activity recommendation subclass is commented.

Further, the step of obtaining the total number of times that each activity recommendation subclass is pushed during each activity stage specifically includes:

based on a preset second algorithm formula:

acquiring the total times of pushing of each activity recommendation subclass in each activity stage, wherein h is the preset duration of the current activity stage, and m is the pushing frequency in the current activity stage; n is the single push volume at the current active phase.

Further, the step of obtaining the parameter value of the current activity stage specifically includes:

presetting an initial click rate, and taking the initial click rate as a parameter value p in a test period stage;

based on the total times of pushing of each activity recommendation subclass in the test period stage and the promotion period stage and the times of clicking of each activity recommendation subclass;

counting the proportion of the number of times that each activity recommendation subclass is clicked to the total number of times that the activity recommendation subclass is pushed in the test period stage, taking the proportion as the click rate of each activity recommendation subclass in the test period, and taking the click rate of the test period as the parameter value p in the promotion period stage;

and counting the proportion of the clicked times of each activity recommendation subclass to the total pushed times in the test period stage and the promotion period stage to serve as an accumulated click rate, and taking the accumulated click rate as a parameter value p in the optimization period stage.

Further, the step of screening out the active primary users based on the pushing result specifically includes:

in the activity test period stage, determining the primary selection users of each activity recommendation subclass based on the monitoring components and preset confirmation conditions;

and taking the activity distinguishing labels of the activity recommendation subclasses as activity labels of corresponding primary users, and counting the activity labels corresponding to the primary users respectively based on a preset statistical model.

Further, the step of determining the primary users of each activity recommendation subclass based on the monitoring component and the preset confirmation condition specifically includes:

the monitoring component monitors a behavior of a user;

if the monitoring component monitors that the number of times that a non-specific user clicks any activity recommendation subclass exceeds a preset number threshold value, taking the non-specific user as a primary user of the activity recommendation subclass;

if the monitoring component monitors that a non-specific user completes the recommendation task of a certain activity recommendation subclass, taking the non-specific user as a primary user of the activity recommendation subclass;

and if the monitoring component monitors that a non-specific user comments on a certain activity recommendation subclass, taking the non-specific user as a primary user of the activity recommendation subclass.

Further, the step of screening out the active target users based on the pushing result specifically includes:

judging whether the number of the active tags corresponding to the primary selection user reaches a preset active tag number threshold value or not in a promotion period stage;

if the number of the active tags corresponding to the initially selected user reaches a preset active tag number threshold value, taking the initially selected user as a target user in an activity promotion period stage;

and if the number of the active labels corresponding to the initially selected user does not reach the preset active label number threshold, re-executing the initial user screening in the active test period.

Further, the step of screening out the active target users based on the pushing result further includes:

the method comprises the steps of grouping activity distinguishing labels of all activity recommendation subclasses in advance, and judging whether the total click rate of the activity recommendation subclasses in all groups in an optimization period stage reaches a preset click rate threshold value or not;

if so, screening out target users in the promotion period which simultaneously accord with all activity distinguishing labels in the group as target users in the optimization period;

and if not, re-executing the initial user screening in the activity test period stage and the target user screening in the activity promotion period stage.

In order to solve the above technical problem, an embodiment of the present application further provides an apparatus for screening a target user, which adopts the following technical solutions:

an active target user screening apparatus comprising:

the preparation module is used for acquiring the remaining denomination, the remaining days and the preset duration of the activity stage when the current activity stage is started, wherein the activity stage comprises the following steps: testing period, promotion period and optimization period;

the target exposure amount determining module is used for acquiring a parameter value of the current activity stage and is based on a preset first algorithm formula:

determining the target exposure amount per hour in the current activity stage, wherein x is the remaining denomination of activity in the current activity stage, d is the remaining days of activity in the current activity stage,p is a parameter value of the current activity stage, and h is a preset duration of the current activity stage;

the pushing result acquisition module is used for performing activity pushing in each activity stage based on the target exposure and acquiring the pushing result in each activity stage;

and the user screening module is used for screening out the activity initial selection user and the activity target user based on the pushing result.

Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:

the embodiment of the application discloses a screening method for activity target users, which determines target exposure per hour in each activity stage through a preset algorithm model, based on the target exposure, the activity pushing of each activity stage is carried out, the pushing result of each activity stage is obtained, based on the pushing result, an activity primary selection user and an activity target user are selected, the screening of the primary selection user in an activity recommendation testing period stage is realized, the target user is selected in an activity recommendation promotion period stage, the target user is further re-selected in an activity recommendation optimization period stage, wherein when the screening is carried out again, the screening is not carried out in a mode of reporting the user, the multi-source screening is carried out from an activity recommendation interface according to a preset monitoring component, a single selection source is avoided, the rule configuration is not rich, the screening of user groups is not enough, and the accurate screening of the target users can be better.

Drawings

In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for activity target user screening according to the present application;

FIG. 3 is a flowchart of one embodiment of the filtering of the target users during the promotion period in step S4 shown in FIG. 2;

FIG. 4 is a flowchart of one embodiment of the target user filtering during the optimization period of step S4 shown in FIG. 2;

FIG. 5 is a schematic diagram illustrating an embodiment of an activity target user screening apparatus according to the present application;

FIG. 6 is a schematic diagram of a structure of an embodiment of 504 shown in FIG. 5;

FIG. 7 is a block diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, motion Picture Experts Group Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion Picture Experts Group Audio Layer 4), a laptop portable computer, a desktop computer, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the

terminal devices

101, 102, 103.

It should be noted that, the activity target user screening method provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the activity target user screening apparatus is generally disposed in the server/terminal device.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continuing reference to FIG. 2, a flow diagram of one embodiment of an activity target user screening method in accordance with the present application is shown. The method for screening the activity target users comprises the following steps:

step S1, when entering a current activity stage, obtaining the remaining denomination, the remaining days and the preset duration of the activity stage, wherein the activity stage comprises the following steps: a testing period, a promotion period and an optimization period.

S2, acquiring a parameter value of the current activity stage, and based on a preset first algorithm formula:

and determining the target exposure per hour in the current activity stage, wherein x is the activity remaining denomination in the current activity stage, d is the activity remaining days in the current activity stage, p is the parameter value of the current activity stage, and h is the preset duration of the current activity stage.

In this embodiment, the step of obtaining the parameter value of the current activity stage specifically includes: presetting an initial click rate, and taking the initial click rate as a parameter value p in a test period stage; based on the total times of pushing of each activity recommendation subclass in the test period stage and the promotion period stage and the times of clicking of each activity recommendation subclass; counting the proportion of the number of times that each activity recommendation subclass is clicked to the total number of times that the activity recommendation subclass is pushed in the test period stage, taking the proportion as the click rate of each activity recommendation subclass in the test period, and taking the click rate of the test period as the parameter value p in the promotion period stage; and counting the proportion of the clicked times of each activity recommendation subclass to the total pushed times in the test period stage and the promotion period stage to serve as an accumulated click rate, and taking the accumulated click rate as a parameter value p in the optimization period stage.

The initial click rate, the test period click rate and the accumulated click rate are respectively used as parameter values of a test period stage, a promotion period stage and an optimization period stage and are transmitted into the preset first algorithm formula, so that the situation that the whole activity recommendation stage only uses a single click rate as a parameter is avoided, the activity recommendation is more scientific, and the accurate screening can be realized.

In the embodiment, the target exposure amount per hour in each activity stage is determined by combining the remaining name of the activity, the remaining days, the preset duration of the activity stage and the parameter value of each activity stage through a preset first algorithm formula.

In this embodiment, the target exposure amount corresponding to each activity phase is used as the single pushing amount in the activity phase.

In the embodiment, different requirements of activity recommendation on the target exposure amount in the test period, the promotion period and the optimization period are combined, the target exposure amount corresponding to different activity stages is respectively used as the single pushing amount in the activity stage, wherein the single pushing amount represents the number of non-specific users selected in the pushing process at the current time, the activity exposure is more scientific, and the exposure amount is prevented from being fixed in each activity stage.

And S3, performing activity pushing in each activity stage based on the target exposure amount to obtain pushing results in each activity stage.

In this embodiment, the step of obtaining the push result of each activity stage specifically includes: partitioning each activity recommendation subclass in an activity recommendation interface in advance, and setting an activity distinguishing label for each activity recommendation subclass; based on a preset monitoring component, acquiring the total number of times that each activity recommendation subclass is pushed in each activity stage, the number of times that each activity recommendation subclass is clicked, a click user identifier when each activity recommendation subclass is clicked, a completion user identifier when a recommendation task of each activity recommendation subclass is completed, and a comment user identifier when each activity recommendation subclass is commented.

In this embodiment, each activity recommendation subclass in the activity recommendation interface is partitioned in advance, an activity distinction tag is set for each activity recommendation subclass, and a preset monitoring component is combined to dynamically monitor click events, push events, task events and comment events in the activity recommendation interface.

In this embodiment, the step of obtaining the total number of times that each activity recommendation subclass is pushed in each activity phase specifically includes: based on a preset second algorithm formula:

By presetting the second algorithm formula, the total recommendation times of each activity stage can be dynamically adjusted by adjusting the push frequency according to the requirements of the activity recommender, so that the activity recommendation times are prevented from being too few.

And S4, screening out the activity initial selection user and the activity target user based on the pushing result.

In this embodiment, the step of screening out the active primary selection user based on the pushing result specifically includes: in the activity test period, determining the primary selection users of each activity recommendation subclass based on the monitoring components and preset confirmation conditions; and taking the activity distinguishing labels of the activity recommendation subclasses as activity labels of corresponding primary users, and counting the activity labels corresponding to the primary users respectively based on a preset statistical model.

In this embodiment, the step of taking the activity distinguishing label of each activity recommendation subclass as the activity label corresponding to the primary user, and counting the activity labels corresponding to each of the primary users based on a preset statistical model is assumed that three activity recommendation subclasses are set on the activity recommendation interface, which are respectively a first recommendation class, a second recommendation class and a third recommendation class, the activity distinguishing labels of the first recommendation class, the second recommendation class and the third recommendation class are respectively one, two and three, the primary user corresponding to the first recommendation class has [ xiao, xiao qiao, xiao grand, xiao li ], the activity distinguishing label "one" is set as the activity label of xiao, xiao grand, xiao lie, the first choice users corresponding to the second recommendation category have [ xiao, xiao sun, xiao week, xiao king ], the activity distinguishing label "two" is set as the activity label of xiao, xiao sun, xiao week, xiao king, the first choice users corresponding to the third recommendation category have [ xiao, xiao money, xiao sun, xiao li ], the activity distinguishing label "three" is set as the activity label of xiao liu, xiao money, xiao sun, xiao li, then the activity label corresponding to each first choice user is respectively counted, namely the activity label corresponding to xiao has [ first, two ], the activity label corresponding to xiao has [ first, three ], the activity label corresponding to xiao sun has [ first, two, three ], the activity label corresponding to xiao li has [ first, three ], the activity label corresponding to xiao week has [ second ], the activity label corresponding to xiao has [ second ], and the activity label corresponding to xiao has [ second ].

The activity distinguishing labels of the activity recommendation subclasses are directly set as the activity labels of the corresponding primary users, and then the number of the activity distinguishing labels corresponding to the primary users is counted, so that a rear program can conveniently screen target users through the primary users.

In this embodiment, the step of determining the primary users of each activity recommendation subclass based on the monitoring component and the preset confirmation condition specifically includes: the monitoring component monitors a behavior of a user; if the monitoring component monitors that the number of times that a non-specific user clicks any activity recommendation subclass exceeds a preset number threshold value, taking the non-specific user as a primary user of the activity recommendation subclass; if the monitoring component monitors that a non-specific user completes the recommendation task of a certain activity recommendation subclass, taking the non-specific user as a primary user of the activity recommendation subclass; and if the monitoring component monitors that a non-specific user comments on a certain activity recommendation subclass, taking the non-specific user as a primary user of the activity recommendation subclass.

According to the embodiment, the user who accords with the preset click times of the activity, completes the activity task and comments on the activity is selected as the initial user through the monitoring component in the activity test period instead of acquiring the registration information as the initial user through the registration user, so that the situation that the initial user is acquired only through the user tag in the past is avoided, and the source is not single any more during data screening.

In this embodiment, the step of screening out the active target user based on the pushing result specifically includes: judging whether the number of the active tags corresponding to the primary selection user reaches a preset active tag number threshold value or not in a promotion period stage; if the number of the active tags corresponding to the initially selected user reaches a preset active tag number threshold value, taking the initially selected user as a target user in an activity promotion period; and if the number of the active labels corresponding to the initially selected users does not reach the preset active label number threshold value, re-executing the initial user screening in the active test period.

With continuing reference to fig. 3, fig. 3 is a flowchart of one embodiment of the step S4 of fig. 2 for performing target user filtering during the promotion period, including:

step S41, judging whether the number of the active tags corresponding to the primary selection user in the promotion period stage reaches a preset active tag number threshold value;

step S42, if the number of the activity labels corresponding to the initially selected user reaches a preset activity label number threshold value, taking the initially selected user as a target user in an activity promotion period;

and S43, if the number of the activity labels corresponding to the initially selected users does not reach the preset activity label number threshold, re-executing the initial user screening in the activity test period.

And screening target users from the primary users determined in the test period in the promotion period through preset activity target user screening conditions, and if the target users do not exist, executing the activity test period stage again in time, so that the activity recommendation mechanism is more met, and meanwhile, the accurate screening of the activity target users is ensured.

In this embodiment, the step of screening out the active target user based on the push result further includes: the method comprises the steps of grouping activity distinguishing labels of all activity recommendation subclasses in advance, and judging whether the total click rate of the activity recommendation subclasses in all groups in an optimization period stage reaches a preset click rate threshold value or not; if so, screening out target users in the promotion period which simultaneously accord with all activity distinguishing labels in the group as target users in the optimization period; and if not, re-executing the initial user screening in the activity test period stage and the target user screening in the activity promotion period stage.

With continued reference to fig. 4, fig. 4 is a flowchart illustrating an embodiment of the step S4 of fig. 2 for performing target user filtering during the optimization period, including:

step S44, grouping the activity distinguishing labels of each activity recommendation subclass in advance;

step S45, judging whether the total click rate of the activity recommendation subclasses in each group in the optimization period reaches a preset click rate threshold value;

step S46, if yes, screening out target users in the promotion period stage which simultaneously accord with all activity distinguishing labels in the group as target users in the optimization period stage;

and S47, if not, re-executing the initial user screening in the activity test period stage and the target user screening in the activity promotion period stage.

And screening the target users in the optimization period from the target users determined in the promotion period through preset activity target user screening conditions, and if the target users in the optimization period do not exist, re-executing the activity test period stage and the promotion period stage in time, so that an activity recommendation mechanism is better met, and meanwhile, the accurate screening of the activity target users is ensured.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

This application is through the target exposure through every hour when predetermineeing algorithm model and confirming each activity stage, based on target exposure carries out each activity stage activity propelling movement, acquires each activity stage propelling movement result, based on the propelling movement result is selected activity primary election user and activity target user, has realized screening primary election user at activity recommendation test stage, screens target user at activity recommendation extension stage, further rescreens target user at activity recommendation optimization stage, wherein, when screening again, do not screening through the mode of reporting to the name the user, but according to predetermineeing the screening that the monitoring subassembly carries out multisource from activity recommendation interface, single choice source has been avoided, and rule configuration is not abundant, and user crowd screens carefully inadequately, also can be better accomplish target user's accurate screening simultaneously.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

With further reference to fig. 5, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an apparatus for filtering active target users, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.

As shown in fig. 5, the activity target user screening apparatus 500 according to this embodiment includes: a preparation module 501, a target exposure amount determination module 502, a push result acquisition module 503, and a user filtering module 504. Wherein:

a preparing module 501, configured to obtain the remaining denomination, the remaining days, and the preset duration of the activity phase when entering the current activity phase, where the activity phase includes: testing period, promotion period and optimization period;

the target exposure amount determining module 502 is configured to obtain a parameter value of a current activity stage, and based on a preset first algorithm formula:

determining the target exposure per hour in the current activity stage, wherein x is the activity remaining denomination in the current activity stage, d is the activity remaining days in the current activity stage, p is a parameter value in the current activity stage, and h is the preset duration in the current activity stage;

a pushing result obtaining module 503, configured to perform activity pushing in each activity stage based on the target exposure amount, and obtain a pushing result in each activity stage;

and the user screening module 504 is configured to screen out the activity primary selection user and the activity target user based on the pushing result.

The activity target user screening device determines the target exposure per hour in each activity stage through the target exposure determining module, acquires the pushing result of each activity stage through the pushing result acquiring module, and the user screening module screens out the activity primary selection user and the activity target user based on the pushing result, so that the primary selection user is screened in the activity recommendation testing period stage, the target user is screened in the activity recommendation promotion period stage, and the target user is further screened in the activity recommendation optimization period stage.

Referring to fig. 6, which is a schematic structural diagram of an embodiment of the target user screening module, the user screening module 504 includes a test period screening submodule 5041, a promotion period screening submodule 5042, and an optimization period screening submodule 5043,

the test period screening submodule 5041 is used for pushing results in the test period stage and screening out the active primary users;

a promotion period screening submodule 5042, configured to screen out an activity promotion period stage target user based on a promotion period stage push result;

and the optimization stage screening submodule 5043 is used for screening out target users in the activity optimization stage based on the optimization stage pushing result.

Through activity recommendation of sub-modules in different stages, initial selection users in a testing period stage are sequentially obtained, target users in a promotion period stage and target users in an optimization period stage are further obtained, and accurate screening of the target users is guaranteed.

In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 7 in particular, fig. 7 is a block diagram of a basic structure of a computer device according to the embodiment.

The computer device 7 comprises a memory 71, a processor 72, a network interface 73, which are communicatively connected to each other via a system bus. It is noted that only a computer device 7 having components 71-73 is shown, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.

The memory 71 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 71 may be an internal storage unit of the computer device 7, such as a hard disk or a memory of the computer device 7. In other embodiments, the memory 71 may also be an external storage device of the computer device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 7. Of course, the memory 71 may also comprise both an internal storage unit of the computer device 7 and an external storage device thereof. In this embodiment, the memory 71 is generally used for storing an operating system and various application software installed on the computer device 7, such as computer readable instructions of the active target user screening method. Further, the memory 71 may also be used to temporarily store various types of data that have been output or are to be output.

The processor 72 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 72 is typically used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is configured to execute computer-readable instructions stored in the memory 71 or process data, such as computer-readable instructions for executing the active target user screening method.

The network interface 73 may comprise a wireless network interface or a wired network interface, and the network interface 73 is generally used for establishing a communication connection between the computer device 7 and other electronic devices.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and the embodiments are provided so that this disclosure will be thorough and complete. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that modifications can be made to the embodiments described in the foregoing detailed description, or equivalents can be substituted for some of the features described therein. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields, and all the equivalent structures are within the protection scope of the present application.

Claims

1. A method for screening active target users is characterized by comprising the following steps:

when entering a current activity stage, acquiring the remaining denomination, the remaining days and the preset duration of the activity stage, wherein the activity stage comprises: testing period, promotion period and optimization period;

determining the target exposure per hour in the current activity stage, wherein x is the activity remaining denomination in the current activity stage, d is the activity remaining days in the current activity stage, p is the parameter value of the current activity stage, and h is the preset duration of the current activity stage;

2. The method for screening activity target users according to claim 1, wherein the step of obtaining the push result of each activity stage specifically comprises:

3. The activity target user screening method according to claim 2, wherein the step of obtaining the total number of times of pushing of each activity recommendation subclass in each activity phase specifically comprises:

based on a preset second algorithm formula:

4. The method for screening active target users according to claim 2, wherein the step of obtaining the parameter values of the current active stage specifically includes:

counting the proportion of the clicked times to the total pushed times of each activity recommendation subclass in the test period stage, taking the proportion as the click rate of each activity recommendation subclass in the test period, and taking the click rate in the test period as the parameter value p in the promotion period stage;

5. The method for screening the activity target users according to claim 2, wherein the step of screening the activity initial users based on the pushing result specifically comprises:

in the activity test period, determining the primary selection users of each activity recommendation subclass based on the monitoring components and preset confirmation conditions;

6. The activity target user screening method according to claim 5, wherein the step of determining the initially selected users of each activity recommendation subclass based on the monitoring component and a preset confirmation condition specifically comprises:

the monitoring component monitors a behavior of a user;

if the monitoring component monitors that a non-specific user clicks any activity recommendation subclass and exceeds a preset frequency threshold value, taking the non-specific user as a primary user of the activity recommendation subclass;

7. The method for screening active target users according to claim 5, wherein the step of screening active target users based on the pushing result specifically comprises:

judging whether the number of the active tags corresponding to the initially selected user reaches a preset active tag number threshold value or not in a promotion period stage;

if the number of the active tags corresponding to the initially selected user reaches a preset active tag number threshold value, taking the initially selected user as a target user in an activity promotion period;

and if the number of the active labels corresponding to the initially selected users does not reach the preset active label number threshold value, re-executing the initial user screening in the active test period.

8. The activity target user screening method according to claim 7, wherein the step of screening out the activity target users based on the push result further comprises:

9. An active target user screening device, comprising:

the preparation module is used for acquiring the remaining name, the remaining days and the preset duration of the activity stage when the current activity stage is started, wherein the activity stage comprises the following steps: testing period, promotion period and optimization period;

the target exposure determining module is used for acquiring a parameter value of the current activity stage and is based on a preset first algorithm formula:

10. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed performs the steps of the activity target user screening method of any one of claims 1 to 8.

11. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the activity target user screening method of any one of claims 1 to 8.