CN115809889A

CN115809889A - Intelligent passenger group screening method, system, medium and equipment based on marketing effect

Info

Publication number: CN115809889A
Application number: CN202211731695.1A
Authority: CN
Inventors: 王永强; 冯鹏
Original assignee: Qizhidao Network Technology Co Ltd
Current assignee: Qizhidao Network Technology Co Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-03-17

Abstract

Inputting candidate guest groups containing feature labels into a guest group screening model to obtain primary guest groups, wherein the guest group screening model is obtained based on sample training guest groups in marketing tests and feature label training of each user in the sample training guest groups; and determining a target passenger group based on the initially selected passenger group and the preset number of the passenger groups. By adopting the method and the device, the required target passenger groups can be automatically selected through the passenger group screening model, the passenger group screening efficiency is improved, and the passenger group screening model is provided with scientific passenger group screening conditions, so that the marketing effect after the advertisement is put in the target passenger groups is further improved.

Description

Intelligent passenger group screening method, system, medium and equipment based on marketing effect

Technical Field

The application relates to the technical field of big data, in particular to a method, a system, a medium and equipment for screening intelligent passenger groups based on marketing effects.

Background

With the development of information technology, various internet forums and e-commerce platforms become a main way for consumers to acquire product and service information, so that not only enterprises pay great attention to internet marketing and hire special teams to perform internet marketing, but also the core of internet marketing is to guide consumers to purchase service or products through marketing information such as advertisements and soft texts.

The general marketing platform can filter the customer base, then carry out the input of advertisement to the customer base who selects, and to the screening of customer base at present, mostly personnel rely on the business experience, or refer to simple marketing effect and manually select the customer base, then constantly optimize the screening condition through the advertisement input test and adjust the screening scheme, and the efficiency of this kind of customer base screening is low to the marketing effect that leads to after the advertisement input is lower.

Disclosure of Invention

In order to scientifically and reasonably screen the customer groups and put advertisements in the customer groups and improve marketing effects, the application provides an intelligent customer group screening method, system, medium and equipment based on marketing effects.

In a first aspect of the present application, a method for screening an intelligent customer group based on a marketing effect is provided, which adopts the following technical scheme:

inputting candidate guest groups containing feature labels into a guest group screening model to obtain primary guest groups, wherein the guest group screening model is obtained by training based on sample training guest groups in a marketing test and feature labels of all users in the sample training guest groups;

and determining a target passenger group based on the initially selected passenger group and the preset number of the passenger groups.

By adopting the technical scheme, the candidate customer groups are input into the pre-trained customer group screening model to obtain a batch of primary customer groups, then the number of the primary customer groups and the number of the preset customer groups based on actual demands are used for determining the target customer groups, the required target customer groups can be automatically screened out through the customer group screening model, the customer group screening efficiency is improved, scientific customer group screening conditions are arranged in the customer group screening model, and the marketing effect after the advertisement delivery is carried out on the target customer groups is further improved.

Optionally, the determining a target customer group based on the initially selected customer group and a preset number of customer groups includes: judging whether the number of the initially selected passenger groups is smaller than the preset number of the passenger groups; if not, arranging the input-output ratios of all users in the primary selected guest group in an ascending order, and screening out guest groups with the number of preset guest groups as target guest groups; if the number of the candidate guest groups is smaller than the number of the candidate guest groups, inputting the guest groups except the candidate guest groups into the guest group screening model to obtain an expansion target guest group; acquiring the compensation passenger group number of the difference between the preset passenger group number and the initially selected passenger group number; and arranging the input-output ratios of all users in the expanded target passenger group according to an ascending order, screening out the passenger groups with the number of the compensation passenger groups, and taking the sum of the passenger groups with the number of the compensation passenger groups and the initial passenger group as the target passenger group.

By adopting the technical scheme, if the number of users of actual demand is small, the users with high user input-output ratio are screened out to serve as the target passenger groups, so that the planning budget is reasonably obtained, the input is reduced, the output is improved, if the number of users of actual demand is large, the passenger groups except the candidate passenger groups are also input into the model to obtain the number of compensation passenger groups, the sum of the number of compensation passenger groups and the number of primary selection passenger groups serves as the target passenger groups, and the final number of target passenger groups meets the actual demand.

Optionally, before the candidate guest group including the feature tag is input into the guest group screening model to obtain the primary guest group, the method further includes: acquiring marketing effect data of a sample customer group in a marketing test; dividing the sample customer base into a positive sample customer base and a negative sample customer base based on the marketing effect data; configuring and screening feature labels of all users in the positive sample guest group to obtain a sample training guest group and the feature labels of all users in the sample training guest group; training an initial passenger group screening model based on the sample training passenger group and the feature labels of the users to obtain a passenger group screening model.

By adopting the technical scheme, the characteristic labels are configured and screened for the user marketing data in the marketing test, the characteristic labels of the sample training customer base and the users are obtained, the model is trained by the scientific customer base screening characteristic labels, and the good marketing effect is achieved after the target customer base screened by the customer base screening model is subjected to advertisement putting.

Optionally, the obtaining marketing effect data of the sample customer base in the marketing test includes: randomly sampling and selecting at least one user as a sample customer group based on the same marketing activity; carrying out marketing test of advertisement putting on the sample customer group; and acquiring marketing effect data of the sample customer group in the marketing test after a preset time period.

By adopting the technical scheme, the marketing test of advertisement putting is carried out by selecting the sample passenger groups based on the same marketing activities, so that the marketing effect data of the sample passenger groups in the marketing test is obtained, and a data source is provided for the training of subsequent samples.

Optionally, the dividing the sample customer base into a positive sample customer base and a negative sample customer base based on the marketing effect data includes: judging whether each user in the sample customer base has response to the marketing test or not based on the marketing effect data; dividing users who respond to the marketing test into positive sample customer groups; users who do not respond to the marketing test are divided into negative sample customer groups.

By adopting the technical scheme, based on marketing effect data, the users responding to the marketing test are divided into the positive sample passenger groups, the interest of the users in the positive sample passenger groups in advertising marketing test is shown, and the positive sample passenger groups interested in advertising marketing can be preliminarily screened out through the division of the sample passenger groups so as to reduce the configuration amount of subsequent feature labels.

Optionally, the configuring and screening feature labels for each user in the positive sample guest group to obtain the feature labels of the sample training guest group and each user in the sample training guest group includes: acquiring marketing effect data of each user in the positive sample customer group; performing feature tag configuration on each user based on the marketing effect data of each user and a preset feature tag library to obtain a feature tag of each user; and screening out the users which do not accord with the preset standard feature labels according to the feature labels of the users to obtain the sample training guest groups and the feature labels of the users in the sample training guest groups.

By adopting the technical scheme, the feature labels are configured for each user in the customer group in the positive sample, so that each user corresponds to a feature label, and the users are conveniently screened according to the feature labels.

Optionally, the screening, according to the feature labels of the users, the users who do not conform to the preset standard feature labels to obtain the feature labels of the sample training customer group and the users in the sample training customer group includes: calculating the correlation degree between the feature label of each user and the corresponding preset standard feature label and the number of the feature labels of each user; screening out users with the number of the feature labels of the users lower than the preset label number to obtain a first sample training guest group; and screening out the users corresponding to the feature labels with the correlation degree lower than the preset correlation degree in the first sample training guest group to obtain the sample training guest group and the feature labels of the users in the sample training guest group.

By adopting the technical scheme, users with less user feature labels are screened out, and users with lower relevancy are screened out, so that sample training customer groups corresponding to feature labels which are screened and reserved at last have the feature of higher feedback on marketing tests, model training is performed according to the sample customer groups and the feature labels of the users, the customer group screening model has a scientific screening function, and the customer group screening efficiency is improved.

In a second aspect of the present application, there is provided an intelligent customer group screening system based on marketing effect, the system comprising:

the system comprises a primary selection guest group acquisition module, a primary selection guest group selection module and a marketing test module, wherein the primary selection guest group acquisition module is used for inputting candidate guest groups containing feature labels into a guest group screening model to obtain primary selection guest groups, and the guest group screening model is obtained based on sample training guest groups in a marketing test and feature label training of each user in the sample training guest groups;

and the target passenger group determining module is used for determining the target passenger group based on the primary selected passenger group and the preset number of the passenger groups.

In a third aspect of the present application, a computer storage medium is provided that stores a plurality of instructions adapted to be loaded by a processor and to perform the above-mentioned method steps.

In a fourth aspect of the present application, there is provided an electronic device comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.

In summary, the present application includes at least one of the following beneficial technical effects:

1. the candidate customer groups are input into a pre-trained customer group screening model to obtain a batch of primary customer groups, then a target customer group is determined based on the number of the pre-set customer groups and the primary customer groups of actual demands, the required target customer group can be automatically screened out through the customer group screening model, the customer group screening efficiency is improved, and the marketing effect after advertisement putting is carried out on the target customer group is further improved due to the fact that scientific customer group screening conditions are arranged in the customer group screening model;

2. the characteristic labels are configured and screened for user marketing data in a marketing test to obtain characteristic labels of sample training customer groups and users, and the model is trained by the aid of the scientific customer group screening characteristic labels, so that a good marketing effect is achieved after advertisement putting is carried out on target customer groups screened by the customer group screening model.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic flowchart of a method for screening an intelligent customer base based on a marketing effect according to an embodiment of the present application;

fig. 2 is a schematic flow chart illustrating passenger group screening model training in an intelligent passenger group screening method based on marketing effect according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart illustrating a target customer group determined in an intelligent customer group screening method based on a marketing effect according to an embodiment of the present application;

fig. 4 is a schematic block diagram of an intelligent customer group screening system based on marketing effect according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Description of the reference numerals: 1. a primary selection guest group acquisition module; 2. a target guest group determination module; 1000. an electronic device; 1001. a processor; 1002. a communication bus; 1003. a user interface; 1004. a network interface; 1005. a memory.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments.

In the description of the embodiments of the present application, the words "exemplary," "for example," or "for instance" are used to indicate instances, or illustrations. Any embodiment or design described herein as "exemplary," "for example," or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "illustrative," "such as," or "for example" are intended to present relevant concepts in a concrete fashion.

In the description of the embodiments of the present application, the term "and/or" is only one kind of association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, B exists alone, and A and B exist at the same time. In addition, the term "plurality" means two or more unless otherwise specified. For example, the plurality of systems refers to two or more systems, and the plurality of screen terminals refers to two or more screen terminals. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the indicated technical feature. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

The general marketing platform can screen user groups, wherein the user groups are user groups possibly interested in the marketing activity, then the screened user groups are put in advertisements, and the screened user groups are guided through marketing information such as advertisements and soft texts, so that the screened user groups are guided to buy services or products. However, at present, for the screening of the customer groups, people mostly manually select the customer groups according to business experiences or by referring to simple marketing effects, and then the screening conditions are continuously optimized through an advertisement putting test to adjust the screening scheme, so that the efficiency of the screening of the customer groups is low, and the marketing effect after the advertisement is put is low.

In the following, the technical solution of the present application and how to solve the above technical problems in the technical solution of the present application are described in detail with reference to specific embodiments, the following embodiments may be combined with each other, and details of the same or similar probabilities or processes may not be described in some embodiments again, and the embodiments of the present application will be described with reference to the drawings below.

In one embodiment, as shown in fig. 1, a flow diagram of an intelligent customer group screening method based on marketing effect is specifically provided. The method is mainly applied to computer equipment, and the specific method comprises the following steps:

step 10: and inputting the candidate guest group containing the feature tag into a guest group screening model to obtain a primary guest group.

In the embodiment of the present application, the candidate guest group may be understood as a group of users, each corresponding to at least one feature tag, selected by a person of the marketing platform through experience or at random. Feature tags may further be understood as tags that represent information or behavioral data of the user, such as the gender of the user, the address to which the user belongs, historical behavioral feedback data of the user for the same marketing campaign, and the like.

The customer group screening model is a user screening model with scientific screening conditions, and is obtained by training sample data for multiple times through marketing tests before application so as to ensure the accuracy of the model. The personnel can input the candidate guest groups containing the feature tags into the guest group screening model, and screening is carried out through the screening conditions in the guest group screening model, so that a batch of primary guest groups are obtained. Compared with the prior art that a person manually selects a customer group through experience, the customer group screening method can realize full-digital automatic screening of the customer group, improves the customer group screening efficiency, and further improves the marketing effect after advertisement putting is carried out on a target customer group due to the fact that scientific customer group screening conditions are arranged in the customer group screening model.

Referring to fig. 2, based on the above embodiment, before inputting the candidate guest group including the feature tag into the guest group screening model to obtain the primary guest group, the training process of the guest group screening model further includes the following steps:

step 101: acquiring marketing effect data of a sample customer group in a marketing test;

in the embodiment of the application, the marketing test can be understood as the same simulated marketing campaign, and the sample customer group refers to a sample customer group formed by at least one user selected by the marketing platform staff through experience or at random. The marketing effect data can be understood as user behavior data of users in the sample customer group in the marketing test, such as browsing amount, transfer amount, click amount, watching dwell time, order placing amount and the like of the users for marketing content in the marketing test.

Specifically, based on the same historical marketing campaign, in a historical user group in the historical marketing campaign, staff of a marketing platform randomly samples and selects at least one user as a sample customer group, and carries out marketing test of advertisement marketing delivery on the sample group, wherein the advertisement marketing can be advertisement characters or video information pushed by the marketing platform so as to guide the user to purchase services or products according to the advertisement information. And after a preset time period, checking the marketing effect data of the sample customer group in the marketing test, namely finishing the marketing test.

For example, if the sample customer base has one thousand users, the marketing effectiveness data of the sample customer base is checked after one month, for example, one hundred users of the one thousand users are not interested in the advertisement information, so the marketing effectiveness data of the one hundred users are all 0, 600 users click to check the advertisement information, 300 users of the 600 users check the advertisement information multiple times or reload and place an order, and the reload amount or the accumulated checking time or the order placing amount of the 300 users is recorded as the marketing effectiveness data.

Step 102: dividing the sample passenger groups into positive sample passenger groups and negative sample passenger groups based on the marketing effect data;

specifically, the computer device obtains behavior data of users of the sample guest group to the advertisement information in the marketing effect data, and determines whether the users have a response to the advertisement information, that is, determines whether the behavior data of the users are all 0. If the user responds to the advertisement information, namely the user is possibly interested in the content in the advertisement information, dividing the users responding to the advertisement information into a positive sample passenger group; if the user does not respond to the advertisement information, that is, the behavior data of the user is all 0, it indicates that the user may not be interested in the content in the advertisement information, and the user who does not respond to the advertisement information is classified as a negative sample guest group. Through the division of the sample passenger groups, a part of negative sample passenger groups which are not interested in the advertisement information can be screened out, so that the subsequent configuration of feature labels on the negative samples is avoided, and the workload is reduced.

Step 103: configuring and screening feature labels for each user in the positive sample guest group to obtain a sample training guest group and the feature labels of each user in the sample training guest group;

in the embodiment of the present application, the feature tag can be understood as basic information representing each user in the sample guest group, and behavior data of each user for the advertisement information.

On the basis of the above embodiment, the step of configuring and screening feature labels for each user in the positive sample guest group to obtain the sample training guest group and the feature labels for each user in the sample training guest group further includes the following steps:

step 1031: acquiring marketing effect data of each user in a positive sample customer group;

specifically, each user in the positive sample guest group has a response to the advertisement information, that is, each user has behavior data for the advertisement information. The computer equipment acquires the marketing effect data of each user in the positive sample customer base, wherein the marketing effect data comprises basic information and behavior data of each user.

Step 1032: performing characteristic label configuration on each user based on the marketing effect data of each user and a preset characteristic label library to obtain the characteristic label of each user;

in the embodiment of the present application, a feature tag library is pre-stored in a computer device, where the feature tag library includes a plurality of feature tags, and the feature tag library may be divided into a classification feature tag and a level feature tag.

For example, the classification characteristic labels may include, but are not limited to, the gender of the user, the location of the user's address, etc.; rating feature tags may include, but are not limited to, a user's interest rating for the advertising information, a user's age rating, and the like. The age class of the user may be determined by determining an age group to which the age of the user belongs according to pre-classified age groups and classes of the age groups. The interest level may be calculated by behavior data of the advertisement information, and specifically, the computer device obtains behavior data of the user on accumulated browsing duration, transfer amount, collection amount, viewing frequency, order release amount, and the like of the advertisement information, scores of each behavior data are performed according to a preset numerical value interval to which each behavior data belongs, the scores are added to obtain a total score of the behavior data of the user, a preset total score interval to which the total score of the user belongs is determined, and the interest level of the user on the advertisement information is determined.

Configuring the feature labels for each user according to the marketing effect data of each user and a preset feature label library, wherein for example, if the gender of the user A is female, the address is Beijing City, the age is 22 years, the browsing time is 15 minutes, the transfer amount is 2, the collection amount is 1, the viewing frequency is 5, and the lower list amount is 0, the feature labels of the user are female, beijing City, age-level youth and interest level are relatively interested. And if the part of the marketing effect data of the user is not successfully matched with the preset feature tag library, the part of the marketing effect data is not matched with the feature tags.

Step 1033: and screening out the users who do not accord with the preset standard feature labels according to the feature labels of the users to obtain the sample training passenger groups and the feature labels of the users in the sample training passenger groups.

Specifically, since each user performs feature tag configuration and the number of feature tags of each user may be different, the computer device obtains the number of feature tags of each user, and screens out users whose number of feature tags is lower than a preset number of tags, for example, if the marketing effect data of the user may have information imperfection and the degree of feature tag configuration is very low, the user is screened out, and a first sample training customer base is obtained. And the computer equipment calculates the relevance between the feature label of each user and the corresponding preset standard label, for example, if the gender of the preset standard feature label is female, the relevance of the user with the feature label of male is low, and the user corresponding to the feature label with the relevance lower than the preset relevance is screened out in the first sample training guest group. And obtaining the sample training guest group and the feature labels of all users in the sample training guest group.

Step 104: training the initial passenger group screening model based on the sample training passenger group and the feature labels of the users to obtain the passenger group screening model.

Specifically, an initial passenger group screening model is constructed, feature tags of users in a sample training passenger group are preprocessed, in this embodiment, the preprocessing process may include a digitization process and a unique hot coding process, the preprocessing process on the feature tags is to adapt the feature tags to computer coding in the same standard form, for example, for one tag feature, if the tag feature has m possible values, after the unique hot coding, the tag feature becomes m binary features, for example, the feature tag of the interest level has no interest, general interest and interest, and after the unique hot coding, the tag is 100, 010 and 001, and the feature tags are mutually exclusive, and only one feature tag can be activated at a time. Inputting the sample training guest group and the preprocessed feature labels of the users into an initial guest group screening model, and performing iterative training on the initial guest group screening model to obtain a guest group screening model. The customer group screening model has the functions of customer group grouping characteristics and corresponding marketing effects.

Step 20: and determining the target passenger group based on the primary selection passenger group and the preset number of the passenger groups.

Specifically, since the candidate guest group is a user selected through the experience of the person or randomly, there may be many users who do not conform to the actual screening condition, so that the number of the users screened at last is small, the number of the initially selected guest groups screened by the guest group screening model needs to be compared with the preset number of guest groups, whether the initially selected guest groups conform to the preset number of guest groups is determined, and if not, the initially selected guest groups need to be expanded to obtain the target guest groups.

Referring to fig. 3, based on the above embodiment, the step of determining the target guest group based on the first selected guest group and the preset number of guest groups further includes the following steps:

step 201: judging whether the number of the initially selected passenger groups is smaller than the preset number of the passenger groups;

specifically, the computer device judges whether the number of the primary selected customer groups is smaller than the number of the preset customer groups, wherein the number of the preset customer groups can be set for marketing platform personnel according to actual demands.

Step 202: if the number of the initially selected customer groups is not smaller than the preset number of the customer groups, arranging the input-output ratios of all the users in the initially selected customer groups in an ascending order, and screening the customer groups with the preset number of the customer groups as target customer groups;

the input-output ratio refers to the ratio of the total investment of the project to the sum of industrial added values output in the operation life period, and in the embodiment of the application, the input-output ratio refers to the ratio of the invested funds of the marketing platform for each user to the income value of the marketing platform after the user places an order. The invested funds of the marketing platform to each user can be assumed to be 1, and the input-output ratio can be set as 1: the N represents the income value of the marketing platform after the user places the order, the smaller the ratio is, namely the larger the N value is, the better the marketing effect is shown, the use input-output ratio can be used for conveniently and intuitively representing the economy of the marketing activity, and the fund use efficiency is directly embodied.

Specifically, if the number of the primary elected customer groups is not less than the number of the preset customer groups, the number of the screened primary elected customer groups can meet the number of the preset customer groups, the input-output ratios of all users in the primary elected customer groups are arranged in an ascending order, the customer groups with the number of the preset customer groups before the smaller input-output ratios are screened out to serve as the target customer groups, the reasonable planning budget can be achieved, the input fund of marketing activities is reduced, and the output income value of marketing activities is improved.

Step 203: if the number of the initially selected guest groups is smaller than the preset number of the guest groups, inputting the guest groups except the candidate guest groups into a guest group screening model to obtain an expansion target guest group;

specifically, if the number of the initially selected customer groups is smaller than the preset number of the customer groups, the number of the customer groups indicating actual requirements is large, the number of the initially selected customer groups cannot meet the preset number of the customer groups, then the customer groups except the candidate customer groups are input into a customer group screening model, the customer groups except the candidate customer groups can be a batch of users selected by marketing platform personnel according to experience or at random, the number of the batch of users can be determined by referring to the screening rate of the initially selected customer groups, and finally a batch of extended target groups are screened out through the customer group screening model.

Step 204: acquiring the compensation passenger group number of the difference between the preset passenger group number and the initial selection passenger group number;

specifically, the computer device obtains a difference value between a preset number of guest groups and an initial number of guest groups as a compensation number of guest groups.

Step 205: and arranging the input-output ratios of all users in the expanded target customer group according to an ascending order, screening out the customer groups with the number of compensation customer groups, and taking the sum of the customer groups with the number of compensation customer groups and the initially selected customer groups as the target customer group.

Specifically, because the number of the expansion target customer groups is generally larger than the number of the compensation customer groups, the number of the expansion target customer groups needs to be screened, similarly, the input-output ratios of all users in the expansion target customer groups are arranged in an ascending order, the customer groups with the compensation customer group number with smaller input-output ratios are screened, and the sum of the customer groups with the compensation customer group number and the customer groups with the initial selection customer group number is used as the target customer group, so that the requirement of the actual customer group number can be met, meanwhile, reasonable planning budget is achieved, the investment of marketing activities is reduced, and the output income value of marketing activities is improved.

In another possible embodiment, if the invested fund budget of the marketing platform is small and the advertisement delivery of a large number of customer groups cannot be performed, the number of the customer groups is reduced, and the invested fund value can be used as a screening condition to control the invested fund of the marketing campaign.

The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.

Referring to fig. 4, an intelligent customer group screening system based on marketing effect according to an embodiment of the present disclosure may include: the system comprises a primary selection passenger group acquisition module 1 and a target passenger group determination module 2, wherein:

the system comprises a primary customer group acquisition module 1, a primary customer group selection module and a customer group selection module, wherein the primary customer group acquisition module is used for inputting candidate customer groups containing feature labels into a customer group screening model to obtain primary customer groups, and the customer group screening model is obtained based on sample training customer groups in marketing tests and feature label training of each user in the sample training customer groups;

and the target passenger group determining module 2 is used for determining the target passenger group based on the primary selected passenger group and the preset number of the passenger groups.

On the basis of the foregoing embodiments, as an optional embodiment, the system for screening an intelligent customer group based on a marketing effect may further include: marketing effect data acquisition module, sample guest crowd divides module, characteristic label configuration module, characteristic label screening module, wherein:

the marketing effect data acquisition module is used for randomly sampling and selecting at least one user as a sample customer group based on the same marketing activities; carrying out marketing test of advertisement delivery on the sample customer group; acquiring marketing effect data of the sample customer group in the marketing test after a preset time period;

the sample guest group dividing module is used for judging whether each user in the sample guest group responds to the marketing test or not based on the marketing effect data; dividing users who respond to the marketing test into positive sample customer groups; dividing users who do not respond to the marketing test into negative sample customer groups;

the characteristic tag configuration module is used for acquiring marketing effect data of each user in the positive sample customer group; performing feature tag configuration on each user based on the marketing effect data of each user and a preset feature tag library to obtain a feature tag of each user;

the characteristic label screening module is used for calculating the correlation degree between the characteristic label of each user and the corresponding preset standard characteristic label and the number of the characteristic labels of each user; screening out users with the number of the characteristic labels of the users lower than the preset label number to obtain a first sample training guest group; and screening out the users corresponding to the feature labels with the correlation degree lower than the preset correlation degree in the first sample training guest group to obtain the sample training guest group and the feature labels of all the users in the sample training guest group.

It should be noted that: in the system provided in the above embodiment, when the functions of the system are implemented, only the division of the functional modules is illustrated, and in practical application, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to implement all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.

An embodiment of the present application further provides a computer storage medium, where the computer storage medium may store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method for screening an intelligent customer group based on a marketing effect according to the embodiment shown above, and a specific execution process may be referred to in specific descriptions of the embodiments shown in fig. 1 to 4, which is not described herein again

Please refer to fig. 5, which is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.

The communication bus 1002 is used to implement connection communication among these components.

The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may further include a standard wired interface and a wireless interface.

The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Processor 1001 may include one or more processing cores, among other things. The processor 1001 connects various parts throughout the server 1000 using various interfaces and lines, and performs various functions of the server 1000 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of Digital Signal Processing (DSP), field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1001, but may be implemented by a single chip.

The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may alternatively be at least one memory device located remotely from the processor 1001. As shown in fig. 5, a memory 1005, which is a computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an application program of a smart guest group filtering method based on marketing effect.

It should be noted that: in the above embodiment, when the device implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.

In the electronic device 1000 shown in fig. 5, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke an application program in the memory 1005 that stores a marketing effect based intelligent guest farm screening method, which when executed by the one or more processors, causes the electronic device to perform the method as described in one or more of the above embodiments.

An electronic device readable storage medium having instructions stored thereon. When executed by one or more processors, cause an electronic device to perform a method as described in one or more of the above embodiments.

It is clear to a person skilled in the art that the solution of the present application can be implemented by means of software and/or hardware. The term "unit" and "module" in this specification refers to software and/or hardware capable of performing a specific function independently or in cooperation with other components, wherein the hardware may be, for example, a Field-ProgrammaBLE Gate Array (FPGA), an Integrated Circuit (IC), or the like.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art will recognize that the embodiments described in this specification are preferred embodiments and that acts or modules referred to are not necessarily required for this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some service interfaces, devices or units, and may be an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application, in essence or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program, which is stored in a computer-readable memory, and the memory may include: flash disks, read-Only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.

The above description is merely an exemplary embodiment of the present disclosure, and the scope of the present disclosure is not limited thereto. It is intended that all equivalent variations and modifications made in accordance with the teachings of the present disclosure be covered thereby. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. An intelligent customer group screening method based on marketing effect is applied to computer equipment, and the method comprises the following steps:

inputting candidate guest groups containing feature labels into a guest group screening model to obtain primary guest groups, wherein the guest group screening model is obtained by training based on sample training guest groups in a marketing test and the feature labels of all users in the sample training guest groups;

and determining a target passenger group based on the primary selection passenger group and the preset number of the passenger groups.

2. The marketing effect-based intelligent customer group screening method according to claim 1, wherein the determining a target customer group based on the primary customer group and a preset number of customer groups comprises:

judging whether the number of the initially selected passenger groups is smaller than the preset number of the passenger groups or not;

if the number of the primary selected guest groups is not smaller than the preset number of guest groups, arranging the input-output ratios of all users in the primary selected guest groups in an ascending order, and screening out the guest groups with the preset number of the guest groups as target guest groups;

if the number of the primary elected guest groups is smaller than the preset number of guest groups, inputting the guest groups except the candidate guest groups into the guest group screening model to obtain an expanded target guest group, obtaining the number of compensated guest groups of the difference between the preset number of guest groups and the number of the primary elected guest groups, arranging the input-output ratios of all users in the expanded target guest group according to an ascending order, screening the guest groups of the number of the compensated guest groups, and taking the sum of the guest groups of the number of the compensated guest groups and the primary elected guest groups as the target guest group.

3. The marketing effect-based intelligent customer group screening method according to claim 1, wherein before inputting the candidate customer groups including the feature tags into the customer group screening model to obtain the primary customer group, the method further comprises:

obtaining marketing effect data of a sample customer group in a marketing test;

dividing the sample customer base into a positive sample customer base and a negative sample customer base based on the marketing effect data;

configuring and screening feature labels of all users in the positive sample guest group to obtain a sample training guest group and the feature labels of all users in the sample training guest group;

training an initial customer group screening model based on the sample training customer group and the feature labels of the users to obtain the customer group screening model.

4. The marketing effect-based intelligent customer base screening method according to claim 3, wherein the obtaining of marketing effect data of a sample customer base in a marketing test comprises:

randomly sampling and selecting at least one user as a sample customer group based on the same marketing activity;

carrying out marketing test of advertisement putting on the sample customer group;

and acquiring marketing effect data of the sample customer group in the marketing test after a preset time period.

5. The marketing effect-based intelligent customer group screening method according to claim 3, wherein the dividing of the sample customer group into a positive sample customer group and a negative sample customer group based on the marketing effect data comprises:

judging whether each user in the sample customer base responds to the marketing test or not based on the marketing effect data;

dividing users who respond to the marketing test into positive sample customer groups;

users who do not respond to the marketing test are divided into negative sample customer groups.

6. The marketing effect-based intelligent customer base screening method according to claim 3, wherein the step of configuring and screening feature labels for each user in the positive sample customer base to obtain a sample training customer base and feature labels for each user in the sample training customer base comprises the steps of:

obtaining marketing effect data of each user in the positive sample customer group;

performing feature tag configuration on each user based on the marketing effect data of each user and a preset feature tag library to obtain a feature tag of each user;

and screening out the users which do not accord with the preset standard feature labels according to the feature labels of the users to obtain the sample training guest groups and the feature labels of the users in the sample training guest groups.

7. The marketing effect based intelligent customer group screening method according to claim 6, wherein the screening of the users who do not meet the preset standard feature labels according to the feature labels of the users to obtain the sample training customer group and the feature labels of the users in the sample training customer group comprises:

calculating the correlation degree between the feature label of each user and the corresponding preset standard feature label and the number of the feature labels of each user;

screening out users with the number of the characteristic labels of the users lower than the preset label number to obtain a first sample training guest group;

and screening out the users corresponding to the feature labels with the correlation degree lower than the preset correlation degree in the first sample training guest group to obtain the sample training guest group and the feature labels of all the users in the sample training guest group.

8. An intelligent customer group screening system based on marketing effect, the system comprising:

the system comprises a primary customer group acquisition module (1) and a primary customer group screening module, wherein the primary customer group acquisition module is used for inputting candidate customer groups containing feature labels into a customer group screening model to obtain the primary customer groups, and the customer group screening model is obtained based on sample training customer groups in marketing tests and feature label training of each user in the sample training customer groups;

and the target passenger group determining module (2) is used for determining the target passenger group based on the primary selected passenger group and the preset passenger group number.

9. A computer-readable storage medium, characterized in that it stores instructions which, when executed, perform the method steps according to any one of claims 1 to 7.

10. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 7.