CN111582944B

CN111582944B - Crowd expansion method, device and equipment for advertisement and storage medium

Info

Publication number: CN111582944B
Application number: CN202010408433.6A
Authority: CN
Inventors: 王玉昕; 郑祺星
Original assignee: Beijing Kingsoft Internet Security Software Co Ltd
Current assignee: Beijing Kingsoft Internet Security Software Co Ltd
Priority date: 2020-05-14
Filing date: 2020-05-14
Publication date: 2023-08-22
Anticipated expiration: 2040-05-14
Also published as: CN111582944A

Abstract

The embodiment of the invention provides a crowd expanding method, device, equipment and storage medium for advertisements, which are used for acquiring first user information of seed users of a first advertiser and second user information of seed users of a second advertiser; wherein the first advertiser is an advertiser of the advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser; crowd expansion is carried out based on the first user information and the second user information respectively, so that third user information of a target user corresponding to the first user information and fourth user information of the target user corresponding to the second user information are obtained; acquiring a seed user of an advertisement to be promoted based on third user information and the fourth user information; and expanding the population based on the seed users of the advertisements to be promoted to obtain target users of the advertisements to be promoted. The scheme can improve the richness of target users expanded by advertisement crowd.

Description

Crowd expansion method, device and equipment for advertisement and storage medium

Technical Field

The invention relates to the technical field of crowd expansion, in particular to a crowd expansion method, device and equipment for advertisements and a storage medium.

Background

In order to reduce the problem of high advertisement promotion cost caused by promotion to all users, crowd expansion can be performed aiming at advertisements to be promoted: and finding a certain number of similar people with relevance as target users of the advertisement to be promoted. Specifically, a plurality of users with relevance to the seed user can be found from a user resource library by a certain algorithm evaluation model based on the seed user and used as target users of advertisements to be promoted.

However, the inventor finds that in the process of implementing the invention, the seed users are often submitted by advertisers and are influenced by factors such as limited user resources owned by the advertisers, the seed users are relatively single, and the target users determined based on the seed users are low in richness.

Disclosure of Invention

The embodiment of the invention aims to provide an expansion method, device, equipment and storage medium, so as to achieve the effect of improving the richness of target users obtained by expansion of advertisement crowd. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a crowd expanding method, including:

acquiring first user information of a seed user of a first advertiser and second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser;

Crowd expansion is carried out based on the first user information to obtain third user information of a target user corresponding to the first user information, and crowd expansion is carried out based on the second user information to obtain fourth user information of the target user corresponding to the second user information;

acquiring seed users of the advertisements to be promoted based on the third user information and the fourth user information;

and expanding the crowd based on the seed users of the advertisements to be promoted to obtain target users of the advertisements to be promoted.

Optionally, the obtaining the first user information of the seed user of the first advertiser includes:

acquiring user information of a first number of users performing specified operations on the product of the first advertiser to obtain first positive user information; wherein the specified operation is an operation regarding advertisement conversion for the advertiser's product;

acquiring user information of a first number of users who do not perform specified operations on the product of the first advertiser, and acquiring first negative user information;

and taking the first positive user information and the first negative user information as first user information of a seed user of the first advertiser.

Optionally, the crowd expansion based on the first user information is performed to obtain third user information of the target user corresponding to the first user information, including:

acquiring information about advertisement conversion results of products of advertisers and information capable of influencing the advertisement conversion results of the products of the advertisers from the first positive user information and the first negative user information of the first user information;

constructing a first user characteristic of a seed user of the first advertiser using the acquired information;

training to obtain a first model for obtaining a first classification result of the user by using the first user characteristics; wherein the first classification result includes: a first positive object type having a user characteristic indicated by the first positive user information or a first negative object type having a user characteristic indicated by the first negative user information;

inputting the user information in the pre-stored user resource library into the first model to obtain a first classification result of the user information in the pre-stored user resource library;

and selecting the obtained first classification result as the user information of the first positive target type as the third user information of the target user corresponding to the first user information.

Optionally, the obtaining the second user information of the seed user of the second advertiser includes:

acquiring user information of a user performing the specified operation on the product of the second advertiser to obtain second positive user information;

acquiring user information of users which are the popularization objects of the products of the second advertiser and do not perform the appointed operation after successful popularization, and acquiring second negative user information;

and taking the second positive user information and the second negative user information as second user information of the seed user of the second advertiser.

Optionally, the crowd expansion based on the second user information is performed to obtain fourth user information of the target user corresponding to the second user information, including:

acquiring information about an advertisement conversion result of a product of an advertiser and information capable of affecting the advertisement conversion result of the product of the advertiser from the second positive user information and the second negative user information of the second user information;

constructing a second user characteristic of the seed user of the second advertiser using the acquired information;

training to obtain a second model for obtaining a second classification result of the user by using the second user characteristics; wherein the second classification result includes: a second positive object type having a user characteristic indicated by the second positive user information or a second negative object type having a user characteristic indicated by the second negative user information;

Inputting the user information in the pre-stored user resource library into the second model to obtain a second classification result of the user information in the pre-stored user resource library;

and selecting the obtained second classification result as user information of a second positive target type as fourth user information of a target user corresponding to the second user information.

Optionally, the obtaining the seed user of the advertisement to be promoted based on the third user information and the fourth user information includes:

promoting the advertisement to be promoted to the initial user indicated by the third user information and the initial user indicated by the fourth user information, and acquiring operation data of each initial user on the advertisement to be promoted;

and selecting a user meeting the preset popularization effect condition from all initial users based on the operation data, and taking the user as a seed user of the advertisement to be promoted.

Optionally, the operation data includes: data indicating whether the advertisement to be promoted is promoted successfully or not, and data indicating whether the specified operation is performed on the advertisement to be promoted or not;

the selecting, based on the operation data, a user satisfying a preset popularization effect condition from among the initial users as a seed user of the advertisement to be promoted, including:

When the operation data indicate that the number of users to be promoted successfully promoted in the advertisement to be promoted is equal to the first number, user information of the users performing the specified operation in the initial users is obtained, and third positive user information is obtained;

acquiring user information of users which are successfully promoted by the advertisement to be promoted and do not perform the specified operation in all initial users, and acquiring third negative user information;

and taking the users corresponding to the third positive user information and the third negative user information as seed users of the advertisements to be promoted.

Optionally, the step of expanding the crowd based on the seed users of the advertisement to be promoted to obtain the target users of the advertisement to be promoted includes:

acquiring information about an advertisement conversion result of the advertisement to be promoted and information capable of influencing the advertisement conversion result of the advertisement to be promoted from the third positive user information and the third negative user information of the seed user of the advertisement to be promoted;

constructing a third user characteristic of the seed user of the advertisement to be promoted by using the acquired information;

training to obtain a third model for obtaining a third classification result of the user by using the third user characteristics; wherein the third classification result includes: a third positive object type having a user characteristic indicated by the third positive user information or a third negative object type having a user characteristic indicated by the third negative user information;

Inputting the user information in the pre-stored user resource library into the third model to obtain a third classification result of the user information in the pre-stored user resource library;

and selecting the user corresponding to the user information of the third positive target type as the target user of the advertisement to be promoted, wherein the obtained third classification result is the user corresponding to the user information of the third positive target type.

In a second aspect, an embodiment of the present invention provides an advertisement crowd expanding device, including:

the user information acquisition module is used for acquiring first user information of a seed user of a first advertiser and acquiring second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser;

the initial user acquisition module is used for carrying out crowd expansion based on the first user information to obtain third user information of a target user corresponding to the first user information, and carrying out crowd expansion based on the second user information to obtain fourth user information of the target user corresponding to the second user information;

the seed user acquisition module is used for acquiring the seed user of the advertisement to be promoted based on the third user information and the fourth user information; the method comprises the steps of carrying out a first treatment on the surface of the

And the target user expansion module is used for expanding the crowd based on the seed users of the advertisements to be promoted to obtain the target users of the advertisements to be promoted.

Optionally, the user information acquisition module is specifically configured to:

Optionally, the initial user acquisition module is specifically configured to:

Optionally, the seed user obtaining module is specifically configured to:

Promoting the advertisement to be promoted to the initial user indicated by the third user information and the initial user indicated by the fourth user information, and acquiring operation data of each initial user on the advertisement to be promoted; and selecting a user meeting the preset popularization effect condition from all initial users based on the operation data, and taking the user as a seed user of the advertisement to be promoted.

the seed user acquisition module is specifically configured to:

Optionally, the target user expansion module includes:

the feature construction sub-module is used for acquiring information about the advertisement conversion result of the advertisement to be promoted and information capable of influencing the advertisement conversion result of the advertisement to be promoted from the third positive user information and the third negative user information of the seed user of the advertisement to be promoted; constructing a third user characteristic of the seed user of the advertisement to be promoted by using the acquired information;

the model training sub-module is used for training to obtain a third model for obtaining a third classification result of the user by utilizing the third user characteristics; wherein the third classification result includes: a third positive object type having a user characteristic indicated by the third positive user information or a third negative object type having a user characteristic indicated by the third negative user information;

the user expansion sub-module is used for inputting the user information in the pre-stored user resource library into the third model to obtain a third classification result of the user information in the pre-stored user resource library; and selecting the user corresponding to the user information of the third positive target type as the target user of the advertisement to be promoted, wherein the obtained third classification result is the user corresponding to the user information of the third positive target type.

In a third aspect, an embodiment of the present invention provides an electronic device, including:

the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the bus; a memory for storing a computer program; and the processor is used for executing the program stored in the memory and realizing the step of the crowd expanding method of the advertisement provided by the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of the crowd expansion method for advertisements provided in the first aspect described above.

In the scheme provided by the embodiment of the invention, the first advertiser is an advertiser of the advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser. Therefore, the first user information of the seed user of the first advertiser is obtained, the second user information of the seed user of the second advertiser is obtained, further population expansion is conducted based on the first user information, the third user information of the target user corresponding to the first user information is obtained, population expansion is conducted based on the second user information, and the fourth user information of the target user corresponding to the second user information is obtained. Based on the information, the obtained seed users of the advertisements to be promoted are more various compared with the seed users provided by the first advertiser for the advertisements to be promoted based on the third user information and the fourth user information, so that the richness of the target users obtained by crowd expansion of the seed users based on the advertisements to be promoted can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

FIG. 1 is a flow chart of a crowd expanding method for advertisement according to an embodiment of the invention;

FIG. 2 is a flowchart illustrating a crowd expansion method for advertisement according to another embodiment of the present invention;

FIG. 3 is a diagram illustrating an exemplary structure of an advertisement crowd expanding device according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of an advertisement crowd expanding device according to another embodiment of the present invention;

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

Detailed Description

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

The crowd expansion method of the advertisement according to the embodiment of the invention is first described below.

The crowd expansion method of the advertisement provided by the embodiment of the invention can be applied to electronic equipment, and the equipment can specifically comprise a desktop computer, a portable computer, an internet television, an intelligent mobile terminal, a server, a wearable intelligent terminal and the like, is not limited herein, and any electronic equipment capable of realizing the embodiment of the invention belongs to the protection scope of the embodiment of the invention.

As shown in fig. 1, the method for expanding the crowd of the advertisement according to an embodiment of the invention may include the following steps:

s101, acquiring first user information of a seed user of a first advertiser and acquiring second user information of a seed user of a second advertiser.

Wherein the first advertiser is an advertiser of the advertisement to be promoted and the second advertiser is a different advertiser from the first advertiser.

In order to improve the richness of the target users obtained based on the subsequent seed user expansion, besides the first user information of the seed users of the first advertiser, the second user information of the seed users of a second advertiser different from the first advertiser can be obtained, and different seed users are increased through different advertisers, so that the diversity of the seed users is improved. In particular applications, the manner in which the first user information of the seed user of the first advertiser is obtained and the second user information of the seed user of the second advertiser is obtained may be varied. For example, first user information of a seed user transmitted by a first advertiser may be received, and similarly, second user information of a seed user transmitted by a second advertiser may be received. Alternatively, for example, a first seed user selection condition sent by the first advertiser may be received, and user information meeting the first seed user selection condition is selected from the user resource library as first user information; similarly, a second seed user selection condition sent by a second advertiser may be received, and user information satisfying the second seed user selection condition is selected from the user resource library as second user information.

Alternatively, for example, different user information may be obtained for whether the user performs an operation regarding advertisement conversion of the advertiser's product. Where ad conversion refers to the operation of a user's identity transitioning from a push object of an ad to a use object of a product in the ad. For example, when the product in the advertisement is a website, the advertisement conversion may include: browse the website, or become a registered user of the website, etc. When the product in the advertisement is APP (Application), the advertisement conversion may include: install APP or activate APP, etc. When the product in the advertisement is an item sold by an e-commerce platform, the advertisement conversion may include: collect the item or purchase the item, etc. For ease of understanding and rational layout, a third exemplary description will be specifically described below in the form of alternative embodiments. Any manner of obtaining the first user information and the second user information may be used in the present invention, which is not limited in this embodiment.

Also, any user information may be plural. By way of example, the user information may be a personalized tag of the user, such as an age tag, a gender tag, and a city tag of the user, etc. Alternatively, the user information may be information affecting the user's preference for the advertiser's product, for example. For example, when the advertiser's product is an APP, the user information may include information of the user-installed APP name, the uninstalled APP name, the operating system of the electronic device used by the user, and the brand of the electronic device, among others. When the advertiser's product is an item sold by an e-commerce platform, the user information may include information such as items the user browses at the e-commerce platform, items collected, items not of interest, and items purchased.

S102, crowd expansion is conducted based on the first user information to obtain third user information of the target user corresponding to the first user information, and crowd expansion is conducted based on the second user information to obtain fourth user information of the target user corresponding to the second user information.

In a specific application, the manner of crowd expansion based on the user information of the seed user may be various. For example, when the personalized tag exists in the user information of the seed user, the user information of the user with the same personalized tag as the seed user can be selected from the user resource library, so as to obtain the user information of the target user. Alternatively, exemplary, the user information of the seed user may be classified according to whether the seed user is interested in the advertiser's product, the user information of the seed user interested in the advertiser's product may be used as positive user information, and the user information of the seed user not interested in the advertiser's product may be used as negative user information; and training the positive user information and the negative user information to obtain a classification model, classifying the users in the user resource library by using the classification model obtained by training, and taking the user information with the type of the positive user information as the user information of the target user. Alternatively, for example, when the seed user has a friend relationship in the social network, user information of friends of the seed user may be used as user information of the target user.

When crowd expansion is performed based on the first user information to obtain third user information of the target user corresponding to the first user information, and crowd expansion is performed based on the second user information to obtain fourth user information of the target user corresponding to the second user information, the crowd expansion mode in any one of the above exemplary descriptions can be adopted, and the difference is that the user information of the seed user can be replaced with the first user information or the second user information in a targeted manner. The second exemplary description will be specifically described in terms of alternative embodiments for ease of understanding and rational layout.

And S103, acquiring a seed user of the advertisement to be promoted based on the third user information and the fourth user information.

In a specific application, the seed user who obtains the advertisement to be promoted based on the third user information and the fourth user information may be various, and will be specifically described in the form of alternative embodiments.

In an optional implementation manner, the obtaining the seed user of the advertisement to be promoted based on the third user information and the fourth user information may specifically include the following steps:

and using the user indicated by the third user information and the user indicated by the fourth user information as seed users of the advertisements to be promoted.

In another optional implementation manner, the obtaining the seed user of the advertisement to be promoted based on the third user information and the fourth user information may specifically include the following steps:

promoting advertisements to be promoted to the initial users indicated by the third user information and the initial users indicated by the fourth user information, and acquiring operation data of the advertisements to be promoted of all the initial users;

In a specific application, if the diversity of the seed users is arbitrarily expanded, the number of invalid users which are not interested in the advertisement to be promoted in the expanded seed users may be excessive, and thus the target users determined based on the seed users are not accurate enough. In order to reduce users not interested in the advertisement to be promoted in all the initial users, so as to improve the accuracy of the target users determined later, the advertisement to be promoted can be promoted to the initial users indicated by the third user information and the initial users indicated by the fourth user information, the operation data of the advertisement to be promoted of all the initial users are obtained, and the users meeting the preset promotion effect conditions are selected from all the initial users based on the operation data to serve as seed users of the advertisement to be promoted.

And, the operation data of the advertisement to be promoted by each initial user can be obtained, and the operation data can be various. For example, operation data of the advertisement to be promoted by each initial user may be requested from the electronic device of the user that received the advertisement to be promoted. Or, for example, the operation data of the advertisement to be promoted by each initial user may be requested from the electronic device corresponding to the advertisement to be promoted. For example, the electronic device corresponding to the advertisement to be promoted may be a server of the video APP for displaying the advertisement. The preset promotion effect conditions are conditions for selecting users interested in advertisements to be promoted from all initial users. For easy understanding and reasonable layout, the following description will specifically describe the step S104 in the embodiment of fig. 2 of the present invention.

According to the alternative embodiment, the advertisements to be promoted are promoted by the initial users indicated by the third user information and the initial users indicated by the fourth user information, and operation data of the advertisements to be promoted of all the initial users are obtained; and further, based on the operation data, the users meeting the preset promotion effect conditions are selected from all the initial users and used as seed users of the advertisements to be promoted, the users which are relatively more interested in the advertisements to be promoted in the initial users can be screened and obtained as target users, and the accuracy of the target users of the advertisements to be promoted is improved, so that the richness and the accuracy of the target users obtained by the expansion of advertisement crowd are considered.

The operation data may specifically include: data indicating whether the advertisement to be promoted is promoted successfully and/or data indicating whether the advertisement to be promoted is subjected to specified operation. For example, the data indicating whether the advertisement to be promoted is successful may include: whether the advertisement to be promoted is successfully displayed on the electronic equipment of the user or whether the advertisement to be promoted is successfully pushed to the electronic equipment of the user. The data indicating whether the advertisement to be promoted is subjected to the specified operation may include: when the advertisement to be promoted contains the APP, the advertisement can be data about the user to install the APP, such as data for requesting a download link of the APP, requesting an installation package of the APP, and the like; or, it may be data about the user activating the APP, such as data for registering the APP and a request for acquiring a verification code.

S104, based on the seed users of the advertisements to be promoted, crowd expansion is carried out, and the target users of the advertisements to be promoted are obtained.

The specific way of expanding the crowd based on the seed users of the advertisement to be promoted to obtain the target users of the advertisement to be promoted is similar to the way of expanding the crowd based on the user information of the seed users in step S102 to obtain the target users corresponding to the user information of the seed users. The difference is that the seed user is the seed user of the advertisement to be promoted in step S104. In order to facilitate understanding and reasonable layout, in the optional embodiment of fig. 2 of the present invention, the manner of expanding the population of the seed users based on the advertisement to be promoted to obtain the target users of the advertisement to be promoted is described in detail.

In an optional implementation manner, the acquiring the first user information of the seed user of the first advertiser may specifically include the following steps:

acquiring user information of a first number of users performing specified operations on products of a first advertiser to obtain first positive user information; wherein the operation is designated as an operation with respect to advertisement conversion of the advertiser's product;

Acquiring user information of a first number of users who do not perform specified operations on a product of a first advertiser, and acquiring first negative user information;

the first positive user information and the first negative user information are used as first user information of seed users of the first advertiser.

In particular applications, the operations specified with respect to advertising conversion of an advertiser's product may be varied. For example, when the advertiser's product is an APP, the designated operation may be an advertiser installed APP; alternatively, the designated operation may be to purchase the item sold by the advertiser when the advertiser's product is the item sold on the e-commerce platform. Accordingly, the operation not specified may be plural. For example, when the advertiser's product is APP, the unspecified operation may be APP from which the advertiser has never been installed; alternatively, when the advertiser's product is an item sold on an e-commerce platform, the designated operation may be that the advertiser has never purchased the item sold.

Also, since the operation is designated as an operation on advertisement conversion for the advertiser's product, the first positive user information may indicate information of users who are relatively more interested in the first advertiser's advertisement, and the first negative user information may be information of users who are relatively less interested in the first advertiser's advertisement. On the basis, the first positive user information and the first negative user information are used as the first user information of the seed users of the first advertisers, so that users which are relatively easy to accept advertisements and are interested in the advertisements to be promoted are expanded from the user resource library correspondingly.

In an optional embodiment, the crowd expansion based on the first user information may further obtain third user information of the target user corresponding to the first user information, which specifically includes the following steps:

acquiring information about advertisement conversion results of products of advertisers and information capable of influencing the advertisement conversion results of the products of the advertisers from first positive user information and first negative user information of the first user information;

training to obtain a first model for obtaining a first classification result of the user by using the first user characteristics; wherein the first classification result includes: a first positive object type having a user characteristic indicated by first positive user information or a first negative object type having a user characteristic indicated by first negative user information;

inputting the user information in the pre-stored user resource library into a first model to obtain a first classification result of the user information in the pre-stored user resource library;

In particular applications, information about the advertising conversion results of the advertiser's product, as well as information that can affect the advertising conversion results of the advertiser's product, can be varied. For example, when the advertiser's product is APP, information about the advertisement conversion result of the advertiser's product may include: information such as the names of APPs installed, the names of APPs uninstalled, the names of APPs left, and the names of APPs used more frequently than a preset threshold value by a user in a specified period of time, for example, in the last three months. And, information of advertisement conversion results capable of affecting the advertiser's product may include: information about the user's electronic device, such as the brand, size, carrier name, and resident identity of the user, for example, of the intelligent mobile terminal.

Alternatively, for example, when the advertiser's product is an item sold by an e-commerce platform, the information about the ad conversion results of the advertiser's product may include: information such as the name of the item purchased, the name of the item marked as uninteresting, the name of the item collected, and the name of the item shared by the user during a specified period of time, such as the last three months. And, information of advertisement conversion results capable of affecting the advertiser's product may include: information about the user's electronic device, such as the brand, size, carrier name, user's resident identity, etc. of the intelligent mobile terminal.

And, the first user feature of the seed user of the first advertiser is constructed by using the acquired information, which may be that the acquired information is spliced to obtain the first user feature, or the acquired information is formed into an array to obtain the first user feature, or the like. When the first model for obtaining the first classification result of the user is obtained by training by utilizing the first user characteristics, in order to cope with the characteristic that the data size of the first user characteristics of the seed user of the first advertiser is large, a logistic regression model can be selected as a trained model so as to improve training efficiency, and model parameters of the logistic regression model are further adjusted through training so as to obtain the first model. In order to cope with the characteristic that the feature dimension of the first user feature is relatively high, a regular regression function can be added in a summation mode in a cost function used in the logistic regression model training process, the problem that the first model obtained through training is fitted on a certain feature and only user information with the feature is selected in a concentrated mode is solved, and the crowd expansion accuracy is further improved.

In an optional implementation manner, the acquiring the second user information of the seed user of the second advertiser may specifically include the following steps:

Acquiring user information of a user performing specified operation on a product of a second advertiser to obtain second positive user information;

acquiring user information of users which are successfully promoted and do not perform specified operations in users serving as promotion objects of products of a second advertiser, and acquiring second negative user information;

In particular applications, the operations specified with respect to advertising conversion of an advertiser's product may be varied. For example, for a second advertiser, when the advertiser's product is an APP, the designated operation may be installing or activating the advertiser's APP; alternatively, the designated operation may be to purchase the item sold by the advertiser when the advertiser's product is the item sold on the e-commerce platform. Accordingly, the operation not specified may be plural. For example, when the advertiser's product is an APP, the non-designated operation may be that the advertiser's APP has not been installed or activated; alternatively, when the advertiser's product is an item sold on an e-commerce platform, the designated operation may be that the advertiser has never purchased the item sold. Moreover, since the seed user of the second advertiser is usually the historical seed user of the second advertiser, the historical seed user is usually promoted with the advertisement of the advertiser, and therefore, the user information of the user who is the promotion target of the product of the second advertiser and does not perform the designated operation after successful promotion can be obtained, and the second negative user information can be obtained. The promotion success may specifically include an advertisement about the product of the second advertiser, and the promotion or presentation success is pushed or presented to the user who is the promotion target of the product of the second advertiser.

Similar to the first positive user information and the first negative user information, since the operation is designated as an operation regarding advertisement conversion for the advertiser's product, the second positive user information may indicate information of users who are relatively more interested in the second advertiser's advertisement, and the second negative user information may be information of users who are relatively less interested in the second advertiser's advertisement. On the basis, the second positive user information and the second negative user information are used as the second user information of the seed users of the second advertisers, so that users which are relatively easy to accept advertisements and are interested in the advertisements to be promoted are expanded from the user resource library correspondingly.

In an optional embodiment, the crowd expansion based on the second user information may further obtain fourth user information of the target user corresponding to the second user information, and the method specifically may include the following steps:

acquiring information about advertisement conversion results of products of advertisers and information capable of influencing the advertisement conversion results of the products of the advertisers from second positive user information and second negative user information of the second user information;

Training to obtain a second model for obtaining a second classification result of the user by using the second user characteristics; wherein the second classification result comprises: a second positive object type having a user characteristic indicated by second positive user information or a second negative object type having a user characteristic indicated by second negative user information;

inputting the user information in the pre-stored user resource library into a second model to obtain a second classification result of the user information in the pre-stored user resource library;

and selecting the obtained second classification result as the user information of the second positive target type as the fourth user information of the target user corresponding to the second user information.

In particular applications, information about the advertising conversion results of the advertiser's product, as well as information that can affect the advertising conversion results of the advertiser's product, can be varied. Illustratively, to reduce omission to potential users, since the advertiser of the second user is different from the advertiser of the first user, when the product of the advertiser is APP, the information about the ad conversion result of the advertiser's product may include: name of APP installed by the user. And, information of advertisement conversion results capable of affecting the advertiser's product may include: information about the brand and size of the user's electronic device, such as an intelligent mobile terminal.

And, similar to the first user feature: the second user feature of the seed user of the second advertiser is constructed by using the acquired information, and may be that the acquired information is spliced to obtain the second user feature, or the acquired information is formed into an array to obtain the second user feature, or the like. Similar to the first model: when the second model for obtaining the second classification result of the user is trained by using the second user features, in order to cope with the characteristic that the data size of the second user features of the seed user of the second advertiser is large, a logistic regression model can be selected as a trained model to improve training efficiency, and model parameters of the logistic regression model are further adjusted through training to obtain the second model. In order to cope with the characteristic that the characteristic dimension of the second user characteristic is relatively high, a regular regression function can be added in a summation mode in a cost function used in the logistic regression model training process, the problem that the trained second model is fitted on a certain characteristic and only user information with the characteristic is selected in a concentrated mode is solved, and the crowd expansion accuracy is further improved.

As shown in fig. 2, a process of a crowd expansion method for advertisement according to another embodiment of the present invention may include the following steps:

s201, acquiring first user information of a seed user of a first advertiser and acquiring second user information of a seed user of a second advertiser.

S202, crowd expansion is conducted based on the first user information to obtain third user information of the target user corresponding to the first user information, and crowd expansion is conducted based on the second user information to obtain fourth user information of the target user corresponding to the second user information.

The steps S201 to S202 are the same as the steps S101 to S102 in the embodiment of fig. 1 of the present invention, and are not repeated here, and detailed descriptions of the embodiment of fig. 1 of the present invention are described above.

S203, promoting the advertisements to be promoted to the initial users indicated by the third user information and the initial users indicated by the fourth user information, and acquiring operation data of the advertisements to be promoted of all the initial users.

Wherein the operation data includes: data indicating whether or not the advertisement to be promoted is promoted successfully, and data indicating whether or not the advertisement to be promoted is subjected to specified operation.

The above S203 is similar to the alternative embodiment of the fig. 1 embodiment of the present invention regarding step S103, except that defining operation data in S203 includes: data indicating whether or not the advertisement to be promoted is promoted successfully, and data indicating whether or not the advertisement to be promoted is subjected to specified operation. The same parts are not described in detail herein, and the description of the alternative embodiment of fig. 1 of the present invention is described above. The data indicating whether the advertisement to be promoted is successfully promoted may include: and in the electronic equipment of the user for receiving the advertisement to be promoted, data about whether the advertisement to be promoted is successfully displayed or pushed. The data indicating whether the advertisement to be promoted performs the specified operation may include data indicating whether the product in the advertisement to be promoted is installed or activated or purchased, and the like.

S204, when the operation data show that the number of users to be promoted in advertising promotion success is equal to the first number in each initial user, user information of the users performing specified operation in each initial user is obtained, and third positive user information is obtained.

Wherein the first number may be the same as the number of users represented by the first positive user information. When the product in the advertisement to be promoted is the APP, user information of the user who installs or activates the APP in each initial user may be obtained when the advertisement to be promoted is successfully promoted to the first number of users, so as to obtain third positive user information.

S205, obtaining user information of users which are to be promoted, successfully promoted by advertisements and do not perform specified operations in all initial users, and obtaining third negative user information.

When the product in the advertisement to be promoted is the APP, user information of the user who is not installed and activated in each initial user and is promoted successfully only can be obtained when the advertisement to be promoted is successfully promoted to the first number of users, and third negative user information can be obtained.

S206, the users corresponding to the third positive user information and the third negative user information are used as seed users of advertisements to be promoted.

S207, expanding the crowd based on the seed users of the advertisements to be promoted, and obtaining target users of the advertisements to be promoted.

The step S207 is the same as the step S104 in the embodiment of fig. 1 of the present invention, and is not repeated here, and the detailed description of the embodiment of fig. 1 of the present invention is described above.

In this alternative embodiment, since the operation is designated as an operation related to advertisement conversion on the advertiser's product, the third positive user information may indicate information of users who are relatively more interested in the advertisement to be pushed, and the third negative user information may indicate information of users who are relatively less interested in the advertisement to be pushed. On the basis, the users corresponding to the third positive user information and the third negative user information are used as seed users of the advertisements to be promoted, so that users more likely to be interested in the advertisements to be promoted are expanded from the user resource library, and the crowd expansion accuracy is improved.

In an optional embodiment, the foregoing crowd expansion is performed by the seed user based on the advertisement to be promoted, so as to obtain the target user of the advertisement to be promoted, which specifically may include the following steps:

acquiring information about an advertisement conversion result of the advertisement to be promoted and information capable of influencing the advertisement conversion result of the advertisement to be promoted from third positive user information and third negative user information of a seed user of the advertisement to be promoted;

training to obtain a third model for obtaining a third classification result of the user by using the third user characteristics; wherein the third classification result includes: a third positive object type having a user characteristic indicated by third positive user information or a third negative object type having a user characteristic indicated by third negative user information;

inputting the user information in the pre-stored user resource library into a third model to obtain a third classification result of the user information in the pre-stored user resource library;

and selecting the user corresponding to the user information of the third positive target type as the target user of the advertisement to be promoted as the obtained third classification result.

Because the advertiser corresponding to the first user information is the same as the advertiser of the seed user of the advertisement to be promoted, information about the advertisement conversion result of the advertisement to be promoted and information capable of affecting the advertisement conversion result of the advertisement to be promoted in the third positive user information and the third negative user information are similar to the information for obtaining the first user characteristics. When the product in the advertisement to be promoted is APP, the information on the advertisement conversion result of the advertiser's product may include: information such as the names of APPs installed, the names of APPs uninstalled, the names of APPs left, and the names of APPs used more frequently than a preset threshold value by a user in a specified period of time, for example, in the last three months. And, information of advertisement conversion results capable of affecting the advertiser's product may include: information about the user's electronic device, such as the brand, size, carrier name, and resident identity of the user, for example, of the intelligent mobile terminal.

Alternatively, for example, when the product in the advertisement to be promoted is an item sold by an e-commerce platform, the information on the advertisement conversion result of the advertiser's product may include: information such as the name of the item purchased, the name of the item marked as uninteresting, the name of the item collected, and the name of the item shared by the user during a specified period of time, such as the last three months. And, information of advertisement conversion results capable of affecting the advertiser's product may include: information about the user's electronic device, such as the brand, size, carrier name, user's resident identity, etc. of the intelligent mobile terminal.

And, similar to the first user feature, the third user feature of the seed user of the advertisement to be promoted is constructed by using the obtained information, which may be to splice the obtained information to obtain the third user feature, or to compose the obtained information into an array to obtain the third user feature, or the like. Similarly to the first model, when the third model for obtaining the third classification result of the user is obtained by training using the third user feature, in order to cope with the characteristic that the data size of the third user feature of the seed user of the advertisement to be promoted is large, the logistic regression model may be selected as the trained model, so as to improve training efficiency, and further, model parameters of the logistic regression model are adjusted by training, so as to obtain the third model. In order to cope with the characteristic that the characteristic dimension of the third user characteristic is relatively high, a regular regression function can be added in a summation mode in a cost function used in the logistic regression model training process, the problem that the third classification model obtained through training is fitted on a certain characteristic and only user information with the characteristic is selected in a concentrated mode is solved, and the crowd expansion accuracy is further improved.

When the crowd expansion of the advertisement to be promoted is carried out by applying the optional embodiment specifically, the obtained expansion effects comprise: the recall (recovery) is about 84% and the accuracy (precision) is about 84%. The recall rate = the number of users interested in the advertisement to be promoted in the target users obtained by expansion +.a total number of users in the user resource library, and the accuracy rate = the number of users interested in the advertisement to be promoted in the target users obtained by expansion +.a total number of users of the target users obtained by expansion. Therefore, the embodiment of the invention can give consideration to the richness and accuracy of the crowd expansion of advertisements.

Corresponding to the embodiment of the method, the embodiment of the invention also provides a crowd expanding device for advertisement.

As shown in fig. 3, the crowd expanding device for advertisement according to one embodiment of the present invention may include:

a user information obtaining module 301, configured to obtain first user information of a seed user of a first advertiser, and obtain second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser;

The initial user obtaining module 302 is configured to perform crowd expansion based on the first user information to obtain third user information of a target user corresponding to the first user information, and perform crowd expansion based on the second user information to obtain fourth user information of the target user corresponding to the second user information;

a seed user obtaining module 303, configured to obtain a seed user of the advertisement to be promoted based on the third user information and the fourth user information;

and the target user expansion module 304 is configured to perform crowd expansion based on the seed user of the advertisement to be promoted, so as to obtain the target user of the advertisement to be promoted.

Optionally, the user information obtaining module 301 is specifically configured to:

Optionally, the initial user obtaining module 302 is specifically configured to:

Optionally, the seed user obtaining module 303 is specifically configured to:

the seed user obtaining module 303 is specifically configured to:

As shown in fig. 4, the structure of the crowd expanding device for advertisement according to another embodiment of the present invention may include:

a user information obtaining module 401, configured to obtain first user information of a seed user of a first advertiser, and obtain second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser;

An initial user obtaining module 402, configured to perform crowd expansion based on the first user information to obtain third user information of a target user corresponding to the first user information, and perform crowd expansion based on the second user information to obtain fourth user information of the target user corresponding to the second user information;

a seed user obtaining module 403, configured to promote the advertisement to be promoted to the initial user indicated by the third user information and the initial user indicated by the fourth user information, and obtain operation data of each initial user on the advertisement to be promoted; selecting users meeting the preset popularization effect conditions from all initial users based on the operation data, and taking the users as seed users of the advertisements to be popularized;

the target user expansion module 404 includes:

a feature construction submodule 4041, configured to obtain information about an advertisement conversion result of the advertisement to be promoted and information capable of affecting the advertisement conversion result of the advertisement to be promoted in the third positive user information and the third negative user information of the seed user of the advertisement to be promoted; constructing a third user characteristic of the seed user of the advertisement to be promoted by using the acquired information;

A model training sub-module 4042, configured to train to obtain a third model for obtaining a third classification result of the user by using the third feature; wherein the third classification result includes: a third positive object type having a user characteristic indicated by the third positive user information or a third negative object type having a user characteristic indicated by the third negative user information;

a user expansion submodule 4043, configured to input user information in a pre-stored user resource library into the third model, and obtain a third classification result of the user information in the pre-stored user resource library; and selecting the user corresponding to the user information of the third positive target type as the target user of the advertisement to be promoted, wherein the obtained third classification result is the user corresponding to the user information of the third positive target type.

Corresponding to the above embodiment, the embodiment of the present invention further provides an electronic device, as shown in fig. 5, where the device may include:

the device comprises a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory complete communication with each other through the communication bus 504;

a memory 503 for storing a computer program;

the processor 501 is configured to implement the steps of the crowd expansion method for advertisement in any of the above embodiments when executing the computer program stored in the memory 503.

The Memory may include RAM (Random Access Memory ) or NVM (Non-Volatile Memory), such as at least one magnetic disk Memory. Optionally, the memory may be at least one memory device located remotely from the processor.

The processor may be a general-purpose processor, including a CPU (Central Processing Unit ), NP (Network Processor, network processor), etc.; but also DSP (Digital Signal Processor ), ASIC (Application Specific Integrated Circuit, application specific integrated circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.

An embodiment of the present invention provides a computer readable storage medium, including an electronic device, where the computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the crowd expansion method for any advertisement in the embodiment above are implemented.

In yet another embodiment of the present invention, a computer program product comprising instructions that, when executed on a computer, cause the computer to perform the crowd expansion method of advertising as described in any of the above embodiments is also provided.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., by wire (e.g., coaxial cable, fiber optics, DSL (Digital Subscriber Line), digital versatile Disk (DSL)), or wirelessly (e.g., infrared, radio, microwave, etc.), the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc., that contains an integration of one or more available media, the available media may be magnetic media (e.g., floppy Disk, hard Disk, magnetic tape), optical media (e.g., DVD (DigitalVersatile Disc, digital versatile Disk)), or semiconductor media (e.g., SSD (Solid State Disk), etc.).

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus and electronic device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and references to the parts of the description of the method embodiments are only required.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A crowd expansion method for advertising, the method comprising:

acquiring first user information of a seed user of a first advertiser and second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser; the first user information includes: first positive user information and first negative user information, the first positive user information and the first negative user information being information of users interested in and not interested in advertisements of the first advertiser, respectively; the second user information includes: second positive user information and second negative user information, the second positive user information and the second negative user information being information of users interested in and not interested in advertisements of the second advertiser, respectively;

2. The method of claim 1, wherein the obtaining the first user information of the seed user of the first advertiser comprises:

3. The method of claim 2, wherein the expanding the population based on the first user information to obtain third user information of the target user corresponding to the first user information comprises:

4. The method of claim 2, wherein the obtaining second user information for the seed user of the second advertiser comprises:

5. The method of claim 4, wherein the expanding the population based on the second user information to obtain fourth user information of the target user corresponding to the second user information comprises:

6. The method according to any one of claims 2 to 5, wherein the obtaining the seed user of the advertisement to be promoted based on the third user information and the fourth user information comprises:

7. The method of claim 6, wherein the operational data comprises: data indicating whether the advertisement to be promoted is promoted successfully or not, and data indicating whether the specified operation is performed on the advertisement to be promoted or not;

8. The method of claim 7, wherein the expanding the population based on the seed users of the advertisement to be promoted to obtain the target users of the advertisement to be promoted comprises:

9. A crowd expansion device for advertising, the device comprising:

the user information acquisition module is used for acquiring first user information of a seed user of a first advertiser and acquiring second user information of a seed user of a second advertiser; wherein the first advertiser is an advertiser of an advertisement to be promoted, and the second advertiser is an advertiser different from the first advertiser; the first user information includes: first positive user information and first negative user information, the first positive user information and the first negative user information being information of users interested in and not interested in advertisements of the first advertiser, respectively; the second user information includes: second positive user information and second negative user information, the second positive user information and the second negative user information being information of users interested in and not interested in advertisements of the second advertiser, respectively;

the seed user acquisition module is used for acquiring the seed user of the advertisement to be promoted based on the third user information and the fourth user information;

10. The apparatus of claim 9, wherein the user information acquisition module is specifically configured to:

11. The apparatus according to claim 10, wherein the initial user acquisition module is specifically configured to:

12. The apparatus of claim 10, wherein the user information acquisition module is specifically configured to:

13. The apparatus according to claim 12, wherein the initial user acquisition module is specifically configured to:

14. The apparatus according to any one of claims 10 to 13, wherein the seed user acquisition module is specifically configured to:

15. The apparatus of claim 14, wherein the operational data comprises: data indicating whether the advertisement to be promoted is promoted successfully or not, and data indicating whether the specified operation is performed on the advertisement to be promoted or not;

the seed user acquisition module is specifically configured to:

16. The apparatus of claim 15, wherein the target user extension module comprises:

17. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the bus; the memory is used for storing a computer program; the processor being configured to execute a program stored on the memory to perform the method steps of any one of claims 1-8.

18. A computer-readable storage medium, characterized in that the storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-8.