CN110675183B

CN110675183B - Marketing object determining method, marketing popularization method and related devices

Info

Publication number: CN110675183B
Application number: CN201910814725.7A
Authority: CN
Inventors: 马书超; 董泽伟; 朱松岭; 冯健
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-08-30
Filing date: 2019-08-30
Publication date: 2023-10-13
Anticipated expiration: 2039-08-30
Also published as: CN110675183A

Abstract

The embodiment of the application provides a marketing object determining method, a marketing popularization method and a related device. The determining method comprises the following steps: acquiring candidate marketing object groups; and taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model, and predicting to obtain the marketing success rate of the users in the candidate user group. And selecting the users with the marketing success rate meeting the preset requirements from the candidate marketing object groups as target marketing object groups. The marketing popularization method comprises the following steps: respectively inputting at least one motivation interest and behavior characteristics of a third historical marketing activity corresponding to the user in the target marketing object group into a second prediction model, and predicting to obtain a marketing success rate of the motivation interest corresponding to the user in the target marketing object group; and determining target incentive interests matched with users in the target marketing object group from at least one incentive interest based on the forecasting result of the second forecasting model, and delivering.

Description

Marketing object determining method, marketing popularization method and related devices

Technical Field

The embodiment of the application relates to the technical field of data processing, in particular to a marketing object determining method, a marketing popularization method and a related device.

Background

The existing marketing campaign may deliver certain motivational benefits to the user to mobilize the user's emotion. Many factors that determine marketing effectiveness, including: economic factors, demographic factors, social cultural factors, motivational interests, market factors, and the like. Therefore, it is difficult to make a careful incentive equity delivery strategy manually, so that in many cases, the marketing budget is not good after being spent.

In view of this, how to reasonably use the marketing budget to achieve better marketing effect is a technical problem that needs to be solved currently.

Disclosure of Invention

The embodiment of the application aims to provide a marketing object determining method, a marketing popularization method and a related device, which can reasonably use marketing budget to realize better marketing effect.

In order to achieve the above object, embodiments of the present application are realized as follows:

in a first aspect, a method for determining a marketing object is provided, including:

acquiring candidate marketing object groups;

Taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model, and predicting to obtain the marketing success rate of the users in the candidate user group; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user;

and selecting the users with the predicted marketing success rate meeting the preset requirements from the candidate marketing object groups as target marketing object groups to be promoted.

In a second aspect, a marketing promotion method is provided, including:

acquiring a target marketing object group to be promoted;

respectively inputting at least one motivation interest and behavior characteristics of a third historical marketing activity corresponding to the user in the target marketing object group into a second prediction model, and predicting to obtain a marketing success rate of the at least one motivation interest corresponding to the user in the target marketing object group; the second prediction model is obtained by training based on a second training data set, and training data of the second training set comprises behavior characteristics of a fourth historical marketing activity corresponding to a sample user, motivation benefits given by the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits given by the fourth historical marketing activity to the sample user play a marketing effect on the sample user;

Determining target incentive interests matched with the users in the target marketing object group from the at least one incentive interest based on the marketing success rate of the users in the target marketing object group corresponding to the at least one incentive interest;

and delivering matched target incentive interests to users in the target marketing object group.

In a third aspect, there is provided a marketing object determining apparatus including:

the first acquisition module acquires candidate marketing object groups;

the first prediction module predicts the marketing success rate of the users in the candidate user group by taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user;

and the first determining module is used for selecting the users with the predicted marketing success rate meeting the preset requirements from the candidate marketing object groups as target marketing object groups to be promoted.

In a fourth aspect, there is provided an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:

acquiring candidate marketing object groups;

In a fifth aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

Acquiring candidate marketing object groups;

In a sixth aspect, a marketing promotion device is provided, including:

the second acquisition module acquires a target marketing object group to be promoted;

the second prediction module is used for respectively inputting at least one motivation interest and behavior characteristics of a third historical marketing activity corresponding to the user in the target marketing object group into a second prediction model, and predicting to obtain the marketing success rate of the at least one motivation interest corresponding to the user in the target marketing object group; the second prediction model is obtained by training based on a second training data set, and training data of the second training set comprises behavior characteristics of a fourth historical marketing activity corresponding to a sample user, motivation benefits given by the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits given by the fourth historical marketing activity to the sample user play a marketing effect on the sample user;

A second determining module, configured to determine, from the at least one incentive interest, a target incentive interest that matches the users in the target marketing object group based on a marketing success rate of the users in the target marketing object group corresponding to the at least one incentive interest;

and the equity delivery module delivers matched target incentive equity to users in the target marketing object group.

In a seventh aspect, there is provided an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:

acquiring a target marketing object group to be promoted;

In an eighth aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring a target marketing object group to be promoted;

According to the scheme provided by the embodiment of the application, on one hand, the marketing success rate of the users in the candidate marketing object group is predicted and obtained through the first prediction model, and the target marketing object group which can be effectively popularized is determined from the candidate marketing object group according to the marketing success rate of the users, so that the marketing budget can be prevented from being wasted on the users who cannot play a marketing effect. On the other hand, after the target marketing object group is determined, the marketing success rate corresponding to the users in the target marketing object group aiming at different motivation interests is further predicted and obtained through a second prediction model, and the target motivation interests matched with the users in the target marketing object group are selected from the motivation interests for throwing, so that balance is found between ensuring the marketing success rate and reducing the marketing budget expenditure, and the technical effect of using the marketing budget on the blade is realized.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.

Fig. 1 is a schematic step diagram of a method for determining a marketing object according to an embodiment of the present application.

Fig. 2 is a schematic step diagram of a marketing method according to an embodiment of the present application.

Fig. 3 is a schematic diagram of steps of a marketing object determining method and a marketing promotion method combined into an actual application scene.

Fig. 4 is a schematic structural diagram of a marketing object determining device according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of a marketing promotion device according to an embodiment of the present application.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, shall fall within the scope of the application.

As described above, the factors determining the marketing effect are very complex and vary from person to person. Based on manual mode, it is difficult to make careful incentive equity release strategy, and in many cases, good marketing effect is not achieved after marketing budget is spent. Therefore, the application aims to provide a technical scheme capable of solving the problems.

FIG. 1 is a flow chart of a method of determining a marketing object according to an embodiment of the present application. The method shown in fig. 1 may be performed by a corresponding apparatus, including:

step S102, a candidate marketing object group is acquired.

The determination manner of the candidate marketing object group is not unique, and the embodiment of the application is not particularly limited.

Step S104, taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model, and predicting to obtain the marketing success rate of the users in the candidate user group; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user.

Wherein the first predictive model may be, but is not limited to being, a classification model. For example: iterative decision tree models, logistic regression models, random forest models, naive bayes-type and support vector machine models, etc.

It should be understood that different classification models correspond to prediction results of different presentation modes, and embodiments of the present application are not limited in detail. For example, the first predictive model may represent in a binary manner that the user is able to be successfully marketed, or that the user is not able to be successfully marketed. For another example, the first predictive model may represent the size of the probability that the user can be successfully marketed in a scored manner.

And S106, selecting the users with the predicted marketing success rate meeting the preset requirements from the candidate marketing object groups as target marketing object groups to be promoted.

The determination method based on the marketing object shown in fig. 1 can be known as follows: the scheme of the embodiment of the application can predict the marketing success rate of the user based on the first model, and reasonably select the target marketing object group to be promoted according to the marketing success rate, thereby avoiding putting the motivation interests on the user with lower marketing success rate and realizing better marketing effect on the premise of limited marketing budget.

The method according to the embodiment of the present application will be described in detail.

Specifically, the method for determining the marketing object in the embodiment of the application mainly comprises the following stages:

stage one, a candidate marketing object population is determined.

At this stage, inactive users may be determined to be candidate marketing object populations.

And step two, training a first prediction model based on the first training data set.

Specifically, the training data in the first training data set includes behavioral characteristics of the sample user corresponding to the second historical marketing campaign and a label indicating whether the second historical marketing campaign is marketing-effective to the sample user.

And the behavior characteristics of the sample user corresponding to the second historical marketing activities are used as the input of the first prediction model, and the labels indicating whether the second historical marketing activities play a marketing effect on the sample user are used as the output of the first prediction model.

During the training process, the first prediction model outputs training results. The loss function of the first prediction model can be derived based on maximum likelihood estimation, and loss between the training result and the label is calculated based on the loss function. Finally, the weight value of the user characteristic in the first prediction model is optimized for the purpose of reducing loss, so that the training effect is achieved.

In practical application, the stage can determine and obtain a sample user from users in the history marketing popularization, and further analyze whether the second history marketing activity plays a marketing effect on the sample user according to behavior data of the sample user responding to the second history marketing activity.

And stage three, predicting the marketing success rate of the users in the candidate marketing object group.

At this stage, the behavior characteristics of the users in the candidate marketing object group in the first history marketing campaign may be input to the first prediction model, and the marketing success rate of the users in the candidate marketing object group may be predicted by the first prediction model.

Similarly, behavioral characteristics of a user in the candidate marketing target group at the first historical marketing campaign may be determined based on behavioral data of the user in response to the first historical marketing campaign.

It should be noted that, as a reasonable prediction scheme, future results should be predicted based on past data. Therefore, preferably, the time corresponding to the second historical marketing campaign is earlier than the time corresponding to the first historical marketing campaign, so as to ensure that the occurrence time of the behavior feature used in the training phase is earlier than the occurrence time of the behavior feature used in the prediction phase.

And step four, screening the candidate marketing object groups to obtain target marketing object groups to be promoted.

In this stage, users with marketing success rates greater than a preset threshold value in the candidate marketing object group may be determined as target marketing object groups, or a preset number of users may be selected from the candidate marketing object groups as target marketing object groups according to the order of the marketing success rates from high to low.

It should be appreciated that users in the target marketing object group may be considered users that respond to the marketing campaign with a high probability, and thus, delivering incentive interests to users in the target marketing object group may avoid wasting marketing budget to some extent.

In addition, motivational interest is also an important factor in determining whether to play a marketing role for a user. For example, the value of incentive interests is too small, and even if users in the target marketing target group are put in, marketing failure may still be caused. If the value of the incentive equity is too great, the coverage of the delivery is smaller on the premise of limited marketing budget, and the expected marketing benefit cannot be achieved.

Therefore, the embodiment of the application also provides a marketing promotion method which is used for putting proper incentive interests to users.

FIG. 2 is a flow chart of a marketing promotion method according to an embodiment of the present application. The method shown in fig. 2 may be performed by a corresponding apparatus, comprising:

step S202, a target marketing object group to be promoted is obtained.

The target marketing object group can be determined based on the method shown in fig. 1, and is not described herein in detail.

Step S204, respectively inputting at least one motivation interest and behavior characteristics of the third historical marketing activities corresponding to the users in the target marketing object group into a second prediction model, and predicting to obtain marketing success rates of the at least one motivation interest corresponding to the users in the target marketing object group; the second prediction model is obtained by training based on a second training data set, and training data of the second training set comprises behavior characteristics of a sample user corresponding to a fourth historical marketing activity, motivation benefits of the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits of the fourth historical marketing activity to the sample user play a marketing role on the sample user.

Wherein the second predictive model may be, but is not limited to being, a classification model. For example: iterative decision tree models, logistic regression models, random forest models, naive bayes-type and support vector machine models, etc.

It should be understood that different classification models correspond to prediction results of different presentation modes, and embodiments of the present application are not limited in detail. For example, the second predictive model may represent in binary fashion that motivational benefits are available to the user or that motivational benefits are not available to the user. For another example, the second predictive model may represent the magnitude of the probability that the incentive equity was successful in marketing the user in a scored manner.

Step S206, determining the target incentive interests matched with the users in the target marketing object group from the at least one incentive interest based on the marketing success rate of the users in the target marketing object group corresponding to the at least one incentive interest.

Specifically, the step may further determine the target incentive interests matched with the users in the target marketing object group by combining the upper limit of the marketing cost of the combined group and the marketing success rate of the corresponding at least one incentive interest of each user in the target marketing object group.

If the upper limit of the marketing cost is not considered, the incentive equity with smaller limit can be selected as the target incentive equity of the user on the basis of ensuring the marketing success rate.

Step S208, the matched target incentive interests are put into users in the target marketing object group.

In the step, channels such as short messages, pushing, corner marks, waist seals, benefit payment and the like can be adopted to deliver target incentive interests to users in the target user group.

The implementation manner of the target incentive equity is not unique, and may be, as an exemplary introduction, a red package, a coupon, a bonus, etc., which is not particularly limited in the embodiment of the present application.

Based on the marketing promotion method shown in fig. 2, it can be known that: the scheme of the embodiment of the application can predict the marketing success rate of different incentive interests to the user based on the second model, select reasonable target incentive interests to be put into the user according to the prediction result, thereby finding balance between ensuring the marketing success rate and reducing the marketing budget expenditure and realizing the technical effect of using the marketing budget on the blade.

Specifically, the marketing popularization method of the embodiment of the application mainly comprises the following stages:

and in the first stage, a target marketing object group to be promoted is obtained.

Specifically, the target marketing object group to be promoted can be determined based on the marketing object determining method, and the principle is the same, so that the description is omitted here.

And step two, training a second prediction model based on the two training data sets.

Specifically, the training data in the second training data set includes behavioral characteristics of the sample user corresponding to the fourth historical marketing campaign, motivational benefits of the fourth historical marketing campaign to the sample user, and a label indicating whether the motivational benefits of the fourth historical marketing campaign to the sample user are marketing to the sample user. The behavior characteristics of the sample user corresponding to the fourth historical marketing activity and the motivation benefits of the fourth historical marketing activity, which are put into the sample user, are used as the input of the second prediction model, and the labels indicating whether the motivation benefits of the fourth historical marketing activity, which are put into the sample user, play a marketing effect on the sample user are used as the output of the second prediction model.

During the training process, the second predictive model outputs training results. The loss function of the second prediction model can be derived based on maximum likelihood estimation, and loss between the training result and the label is calculated based on the loss function. Finally, the user characteristic weight and the weight value of the motivation rights in the second prediction model are optimized with the aim of reducing loss, so that the training effect is achieved.

In practical application, the stage can determine and obtain a sample user from the users in the history marketing promotion, and further analyze whether the fourth history marketing campaign plays a marketing effect on the sample user according to the behavior data of the sample user responding to the fourth history marketing campaign.

And step three, predicting the marketing success rate of the users in the target marketing object group corresponding to the incentive interests.

In particular, at least one incentive offer may be provided to users in the target marketing object population. Wherein different incentive interests correspond to different interests. The greater the equity, the higher the corresponding marketing success rate and marketing budget expenditure. The smaller the equity, the lower the corresponding marketing success rate and marketing budget expenditure.

And at the stage, respectively inputting the behavior characteristics of the users in the historical third historical marketing activities in different motivation interests and the target marketing object groups into a first prediction model, and predicting the marketing success rate of the users in the target marketing object groups for the different motivation interests by the first prediction model.

Similarly, behavioral characteristics of a user in the target marketing target group in the third historical marketing campaign may be determined based on behavioral data of the user in response to the third historical marketing campaign.

It should be noted that, as a reasonable prediction scheme, future results should be predicted based on past data. Therefore, preferably, the time corresponding to the fourth historical marketing campaign is earlier than the time corresponding to the third historical marketing campaign, so as to ensure that the occurrence time of the behavior feature used in the training phase is earlier than the occurrence time of the behavior feature used in the prediction phase.

And step four, determining the target incentive interests finally put into the users in the target marketing object group from at least one incentive interest based on the marketing success rate of the users of the target marketing object group corresponding to the at least one incentive interest.

Specifically, on the premise that the upper limit of the marketing cost of the target marketing object group is not exceeded, the step can select one with the smallest equity as the target incentive equity in the incentive equity of which the marketing success rate meets a certain requirement.

For example, an incentive equity with a marketing success rate greater than 70% may be identified as producing an effective marketing effect after delivery. Assuming that the equity of the incentive equity is divided into 50, 75 and 100 (the higher the equity value is, the higher the corresponding cost is), the marketing success rate of the incentive equity with equity of 50 to the user A is predicted to be 20% by the marketing success rate prediction model, the marketing success rate of the incentive equity with equity of 75 to the user A is 70%, and the marketing success rate of the incentive equity with equity of 100 to the user A is 85%, the incentive equity with equity of 75 can be used as the target incentive equity of the user A.

In addition, in determining the target incentive interests of the users in the target marketing target group, the adaptability can be adjusted according to the upper limit of the marketing cost of the target user group. For example, after determining the target incentive equity, if the upper limit of the marketing cost of the target user group is exceeded, a part of users may be deleted from the target user group according to a certain preset policy.

And step five, putting matched target incentive interests to users in the target marketing object group.

In this stage, matched target incentive interests can be put in the users in the target marketing object group by means of short messages, pushing, cards, corner marks, waist seals, benefit payment and the like, and because the putting mode is not unique, the description is omitted herein by way of example.

For easy understanding, the method for determining the marketing object shown in fig. 1 and the marketing promotion method shown in fig. 2 are described in the following with reference to the actual application scenario.

In the application scenario, the target payment application stimulates the inactive user to use the target payment application more by putting in the marketing mode of the red envelope equity. The specific flow is shown in fig. 3, and includes:

step S301, determining an inactive user group in the target payment application as a candidate marketing object group.

In this step, the user whose balance in the target payment application does not reach the first preset threshold value and/or the user whose deactivation time in the target payment application reaches the second preset threshold value may be determined as an inactive user group, but not limited to.

Step S302, based on the first prediction model, the marketing success rate of the users in the candidate marketing object group is predicted.

In this step, behavior features of the users in the candidate marketing object group corresponding to the first historical marketing campaign are determined based on the usage data of the users in the candidate marketing object group for the target payment application in the first historical marketing campaign.

And then, the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities are input into a first prediction model, and the marketing success rate of the users in the candidate marketing object group is predicted by the first prediction model.

As described above, the first predictive model is trained by taking as input the behavioral characteristics of the sample user corresponding to the second historical marketing campaign and as output the label indicating whether the second historical marketing campaign is marketing-effect to the sample user.

Wherein the behavioral characteristics of the sample user corresponding to the second historical marketing campaign may be determined based on usage data of the sample user for the target payment application during the second historical marketing campaign period. The label indicating whether the second historical marketing campaign is effective for the sample user may be determined based on whether the sample user received incentive interests offered by the second historical marketing campaign within a period of the second historical marketing campaign and/or based on a change in frequency of use of the sample for the target payment application after receiving the incentive interests offered by the second historical marketing campaign.

In this step, if the sample user receives the interest of the red package delivered by the second historical marketing campaign, and/or the change amount of the frequency of use of the sample user for the target payment application reaches a certain mark (for example, reaches 40% after receiving the interest of the red package delivered by the second historical marketing campaign), the fourth historical marketing campaign is determined to have a marketing effect on the sample user.

Step S303, determining the user which can be effectively stimulated to use the target payment application from the candidate marketing object group as the target marketing object group.

In this step, users of the candidate marketing target group that have a predicted marketing success rate greater than a certain criterion (e.g., 60%) may be determined to be users who can be effectively motivated to use the target payment application.

Step S304, configuring the red packet interests of different red packet amounts for users in the target lost user group.

Step S305, predicting the marketing success rate of the users in the target lost user group for different red pack amounts.

In this step, behavior features of the users in the target marketing object group corresponding to the third historical marketing campaign are determined based on the usage data of the users in the target marketing object group in the third historical marketing campaign for the target payment application.

And then, respectively inputting the behavior characteristics of the third historical marketing activities corresponding to the different red package amounts and the users in the target marketing object group into a second prediction model, and predicting the marketing success rate of the users in the target marketing object group corresponding to the red package amounts by the second prediction model.

As described above, the third predictive model is trained by taking as input the behavioral characteristics of the sample user corresponding to the fourth historical marketing campaign and the different amounts of the red packages, and taking as output the labels indicating whether the different amounts of the red packages have a marketing effect on the sample user.

Wherein the behavioral characteristics of the sample user corresponding to the fourth historical marketing campaign may be determined based on usage data of the sample user for the target payment application during the fourth historical marketing campaign period. The label indicating whether the amount of the red package released by the fourth historical marketing campaign to the sample user has a marketing effect on the sample user is determined based on whether the sample user receives the red package equity released by the fourth historical marketing campaign and/or the amount of change in the frequency of use of the sample user for the target payment application after receiving the red package equity released by the fourth historical marketing campaign.

In this step, if the sample user receives the red-package equity delivered by the fourth historical marketing campaign, and/or the sample user reaches a certain mark (for example, reaches 40% in amplification) for the usage frequency variation of the target payment application after receiving the red-package equity delivered by the fourth historical marketing campaign, the red-package equity delivered by the fourth historical marketing campaign is determined to play a marketing effect on the sample user.

Step S306, determining a matched target red-envelope amount for the users in the target marketing target group.

In the step, the red package equity with the marketing success rate being more than 75% can be considered to generate effective marketing effect after being put in.

Assume that the target marketing object group includes user a, user B, and user C. The red packet rights are divided into 8-element red packets, 15-element red packets and 25-element red packets.

And predicting by a second prediction model to obtain:

the marketing success rate of the user A corresponding to the 8-element red packet is 20%, the marketing success rate of the user A corresponding to the 15-element red packet is 75%, and the marketing success rate of the user A corresponding to the 25-element red packet is 90%.

The marketing success rate of the user B corresponding to the 8-element red packet is 80%, the marketing success rate of the user B corresponding to the 15-element red packet is 90%, and the marketing success rate of the user B corresponding to the 25-element red packet is 95%.

The marketing success rate of the user C corresponding to the 8-element red packet is 0%, the marketing success rate of the user C corresponding to the 15-element red packet is 10%, and the marketing success rate of the user C corresponding to the 25-element red packet is 75%.

Under the premise of not considering marketing budget, the marketing campaign should put in 15-element red packets to the user A, 8-element red packets to the user B and 25-element red packets to the user C.

If the upper marketing cost of the target marketing object group is 40 yuan, a part of users need to be removed from the target marketing object group in order not to exceed the marketing budget. Considering that user C needs to invest 25 yuan to obtain a certain marketing effect, in order to reduce the marketing budget, the step can remove user C from the target marketing object group.

Step S307, the matched red packet interests of the target red packet amount are put into the users in the target marketing object group.

Corresponding to the above method for determining a marketing object, as shown in fig. 4, an embodiment of the present application further provides a device 400 for determining a marketing object, including:

a first obtaining module 410 that obtains candidate marketing object groups;

the first prediction module 420 predicts the marketing success rate of the users in the candidate user group by taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of the first prediction model; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user;

The first determining module 430 selects, from the candidate marketing object groups, a user whose predicted marketing success rate meets a preset requirement as a target marketing object group to be promoted.

The determination means based on the marketing object shown in fig. 4 can know: the scheme of the embodiment of the application can predict the marketing success rate of the user based on the first model, and reasonably select the target marketing object group to be promoted according to the marketing success rate, thereby avoiding putting the motivation interests on the user with lower marketing success rate and realizing better marketing effect on the premise of limited marketing budget.

Optionally, the second historical marketing campaign corresponds to a time earlier than the first historical marketing campaign.

Optionally, the first obtaining module 410, when executed, specifically determines at least some inactive users in the target payment application as candidate marketing object groups; wherein the first historical marketing campaign and the second historical marketing campaign are both marketing campaigns initiated by the target payment application.

Optionally, the inactive user includes: and (3) a user of which the balance does not reach a first preset threshold value in the target payment application and/or a user of which the disabling time reaches a second preset threshold value in the target payment application.

Optionally, the behavior characteristics of the user corresponding to the first historical marketing campaign in the candidate marketing target group are determined based on the usage data of the user for the target payment application in the first historical marketing campaign period;

the behavioral characteristics of the sample user corresponding to the second historical marketing campaign are determined based on usage data of the sample user for the target payment application during the second historical marketing campaign period.

It is obvious that the determining device according to the embodiment of the present application may be the execution subject of the determining method shown in fig. 1 described above, and thus the determining device can implement the functions of the determining method in fig. 1 and 3. Since the principle is the same, the description is not repeated here.

Corresponding to the marketing promotion method, as shown in fig. 5, the embodiment of the application further provides a marketing promotion device 500, which includes:

a second obtaining module 510 for obtaining a target marketing object group to be promoted;

the second prediction module 520 inputs the behavior characteristics of the third historical marketing campaign corresponding to the user in the target marketing object group and at least one kind of motivation interests to a second prediction model to obtain the marketing success rate of the user in the target marketing object group corresponding to the at least one kind of motivation interests; the second prediction model is obtained by training based on a second training data set, and training data of the second training set comprises behavior characteristics of a fourth historical marketing activity corresponding to a sample user, motivation benefits given by the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits given by the fourth historical marketing activity to the sample user play a marketing effect on the sample user;

A second determining module 530 that determines a target incentive interest matching the users in the target marketing object group from the at least one incentive interest based on the marketing success rate of the users in the target marketing object group corresponding to the at least one incentive interest;

and a rights delivery module 540 for delivering the matched target incentive rights to the users in the target marketing object group.

Based on the marketing promotion device shown in fig. 5, it can be known that: the scheme of the embodiment of the application can predict the marketing success rate of different incentive interests to the user based on the second model, select reasonable target incentive interests to be put into the user according to the prediction result, thereby finding balance between ensuring the marketing success rate and reducing the marketing budget expenditure and realizing the technical effect of using the marketing budget on the blade.

Optionally, the time corresponding to the fourth historical marketing campaign is earlier than the time corresponding to the third historical marketing campaign.

Optionally, the third historical marketing campaign and the fourth historical marketing campaign are both marketing campaigns initiated by a target payment application; the behavior characteristics of the users in the target marketing object group corresponding to the third historical marketing activity are determined based on the usage data of the users aiming at the target payment application in the third historical marketing activity period; the behavioral characteristics of the sample user corresponding to the fourth historical marketing campaign are determined based on usage data of the sample user for the target payment application during the fourth historical marketing campaign period.

Optionally, the at least one incentive equity corresponds to mutually different equity amounts.

Optionally, the equity delivery module 540 determines, when executed, a target equity matching the user in the target user group from the at least one equity based on an upper marketing cost limit of the target user group and a marketing success rate of the user in the target user group for the at least one equity.

Obviously, the marketing promotion device of the embodiment of the application can be used as an execution theme of the marketing promotion method shown in the figure 1, so that the marketing promotion device can realize the functions of the marketing promotion method in the figures 2 and 3. Since the principle is the same, the description is not repeated here.

Fig. 6 is a schematic structural view of an electronic device according to an embodiment of the present application. Referring to fig. 6, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.

And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.

The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs, and the determining device of the marketing object can be formed on the logic level and is specifically used for executing the following operations:

acquiring candidate marketing object groups;

Alternatively, the processor may read the corresponding computer program from the nonvolatile memory into the memory and then run, and may form the marketing promotion device on a logic level, and specifically be configured to perform the following operations:

acquiring a target marketing object group to be promoted;

The method for determining the marketing object disclosed in the embodiment shown in fig. 1 of the present application or the method for marketing promotion disclosed in the embodiment shown in fig. 2 of the present application may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It should be understood that the electronic device according to the embodiment of the present application may implement the functions of the embodiment shown in fig. 1 and 3 of the above-mentioned marketing target determination device, or implement the functions of the embodiment shown in fig. 2 and 3 of the above-mentioned marketing promotion device. Since the principle is the same, the description is not repeated here.

Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flow is not limited to each logic unit, but may be hardware or a logic device.

Furthermore, an embodiment of the present application also proposes a computer-readable storage medium storing one or more programs, the one or more programs including instructions.

Wherein. The instructions, when executed by a portable electronic device comprising a plurality of applications, enable the portable electronic device to perform the method of determining a marketing object of the embodiment shown in fig. 1, and in particular to perform the method of:

acquiring candidate marketing object groups;

Alternatively, the instructions, when executed by a portable electronic device comprising a plurality of applications, enable the portable electronic device to perform the marketing method of the embodiment shown in fig. 2, and in particular to perform the method of:

acquiring a target marketing object group to be promoted;

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The foregoing is merely an example of the present specification and is not intended to limit the present specification. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.

Claims

1. A marketing promotion method comprising:

acquiring candidate marketing object groups;

taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model, and predicting to obtain the marketing success rate of the users in the candidate marketing object group; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user;

selecting a user with the predicted marketing success rate meeting the preset requirement from the candidate marketing object group as a target marketing object group to be promoted;

respectively inputting at least one motivation interest and behavior characteristics of a third historical marketing activity corresponding to the user in the target marketing object group into a second prediction model, and predicting to obtain a marketing success rate of the at least one motivation interest corresponding to the user in the target marketing object group; the second prediction model is obtained by training based on a second training data set, and training data of the second training data set comprises behavior characteristics of a fourth historical marketing activity corresponding to a sample user, motivation benefits given by the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits given by the fourth historical marketing activity to the sample user play a marketing effect on the sample user;

2. The method according to claim 1,

the second historical marketing campaign corresponds to a time earlier than the first historical marketing campaign.

3. The method according to claim 1,

obtaining a candidate marketing object group, comprising:

determining at least some inactive users in the target payment application as candidate marketing object groups; wherein the first historical marketing campaign and the second historical marketing campaign are both marketing campaigns initiated by the target payment application.

4. A method according to claim 3,

the inactive user includes: and (3) a user of which the balance does not reach a first preset threshold value in the target payment application and/or a user of which the disabling time reaches a second preset threshold value in the target payment application.

5. The method according to claim 4, wherein the method comprises,

The behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities are determined based on the usage data of the users aiming at the target payment application in the first historical marketing activity period;

6. The method according to claim 1,

the fourth historical marketing campaign corresponds to a time earlier than the third historical marketing campaign.

7. The method according to claim 5,

the third historical marketing campaign and the fourth historical marketing campaign are both marketing campaigns initiated by a target payment application;

the behavior characteristics of the users in the target marketing object group corresponding to the third historical marketing activity are determined based on the usage data of the users aiming at the target payment application in the third historical marketing activity period;

the behavioral characteristics of the sample user corresponding to the fourth historical marketing campaign are determined based on usage data of the sample user for the target payment application during the fourth historical marketing campaign period.

8. The method according to any one of claim 1 to 7,

the at least one incentive equity corresponds to mutually different equity amounts.

9. The method according to any one of claim 1 to 7,

determining a target incentive interest matched with the user in the target marketing object group from the at least one incentive interest based on the marketing success rate of the user in the target marketing object group corresponding to the at least one incentive interest, comprising:

and determining the target incentive interests matched with the users in the target marketing object group from the at least one incentive interest based on the upper limit of the marketing cost of the target marketing object group and the marketing success rate of the users in the target marketing object group corresponding to the at least one incentive interest.

10. A marketing promotion device comprising:

the first acquisition module acquires candidate marketing object groups;

the first prediction module predicts the marketing success rate of the users in the candidate marketing object group by taking the behavior characteristics of the users in the candidate marketing object group corresponding to the first historical marketing activities as the input of a first prediction model; the first prediction model is obtained by training based on a first training data set, and training data in the first training data set comprises behavior characteristics of a sample user corresponding to a second historical marketing activity and labels indicating whether the second historical marketing activity has a marketing effect on the sample user;

The first determining module selects a user with the predicted marketing success rate meeting the preset requirement from the candidate marketing object group as a target marketing object group to be promoted;

the second prediction module is used for respectively inputting at least one motivation interest and behavior characteristics of a third historical marketing activity corresponding to the user in the target marketing object group into a second prediction model, and predicting to obtain the marketing success rate of the at least one motivation interest corresponding to the user in the target marketing object group; the second prediction model is obtained by training based on a second training data set, and training data of the second training data set comprises behavior characteristics of a fourth historical marketing activity corresponding to a sample user, motivation benefits given by the fourth historical marketing activity to the sample user and labels indicating whether the motivation benefits given by the fourth historical marketing activity to the sample user play a marketing effect on the sample user;

11. An electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor:

acquiring candidate marketing object groups;

12. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring candidate marketing object groups;